Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Paolo Bonzini:
 "ARM:
   - GICv4.1 support

   - 32bit host removal

  PPC:
   - secure (encrypted) using under the Protected Execution Framework
     ultravisor

  s390:
   - allow disabling GISA (hardware interrupt injection) and protected
     VMs/ultravisor support.

  x86:
   - New dirty bitmap flag that sets all bits in the bitmap when dirty
     page logging is enabled; this is faster because it doesn't require
     bulk modification of the page tables.

   - Initial work on making nested SVM event injection more similar to
     VMX, and less buggy.

   - Various cleanups to MMU code (though the big ones and related
     optimizations were delayed to 5.8). Instead of using cr3 in
     function names which occasionally means eptp, KVM too has
     standardized on "pgd".

   - A large refactoring of CPUID features, which now use an array that
     parallels the core x86_features.

   - Some removal of pointer chasing from kvm_x86_ops, which will also
     be switched to static calls as soon as they are available.

   - New Tigerlake CPUID features.

   - More bugfixes, optimizations and cleanups.

  Generic:
   - selftests: cleanups, new MMU notifier stress test, steal-time test

   - CSV output for kvm_stat"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (277 commits)
  x86/kvm: fix a missing-prototypes "vmread_error"
  KVM: x86: Fix BUILD_BUG() in __cpuid_entry_get_reg() w/ CONFIG_UBSAN=y
  KVM: VMX: Add a trampoline to fix VMREAD error handling
  KVM: SVM: Annotate svm_x86_ops as __initdata
  KVM: VMX: Annotate vmx_x86_ops as __initdata
  KVM: x86: Drop __exit from kvm_x86_ops' hardware_unsetup()
  KVM: x86: Copy kvm_x86_ops by value to eliminate layer of indirection
  KVM: x86: Set kvm_x86_ops only after ->hardware_setup() completes
  KVM: VMX: Configure runtime hooks using vmx_x86_ops
  KVM: VMX: Move hardware_setup() definition below vmx_x86_ops
  KVM: x86: Move init-only kvm_x86_ops to separate struct
  KVM: Pass kvm_init()'s opaque param to additional arch funcs
  s390/gmap: return proper error code on ksm unsharing
  KVM: selftests: Fix cosmetic copy-paste error in vm_mem_region_move()
  KVM: Fix out of range accesses to memslots
  KVM: X86: Micro-optimize IPI fastpath delay
  KVM: X86: Delay read msr data iff writes ICR MSR
  KVM: PPC: Book3S HV: Add a capability for enabling secure guests
  KVM: arm64: GICv4.1: Expose HW-based SGIs in debugfs
  KVM: arm64: GICv4.1: Allow non-trapping WFI when using HW SGIs
  ...

39 files changed, 1926 insertions, 461 deletions

diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 30072c3f52fb..16877c3daabf 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -1,13 +1,16 @@
-/s390x/sync_regs_test
 /s390x/memop
+/s390x/resets
+/s390x/sync_regs_test
 /x86_64/cr4_cpuid_sync_test
 /x86_64/evmcs_test
 /x86_64/hyperv_cpuid
 /x86_64/mmio_warning_test
 /x86_64/platform_info_test
+/x86_64/set_memory_region_test
 /x86_64/set_sregs_test
 /x86_64/smm_test
 /x86_64/state_test
+/x86_64/svm_vmcall_test
 /x86_64/sync_regs_test
 /x86_64/vmx_close_while_nested_test
 /x86_64/vmx_dirty_log_test
@@ -15,5 +18,7 @@
 /x86_64/vmx_tsc_adjust_test
 /x86_64/xss_msr_test
 /clear_dirty_log_test
+/demand_paging_test
 /dirty_log_test
 /kvm_create_max_vcpus
+/steal_time
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index d91c53b726e6..712a2ddd2a27 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -7,7 +7,7 @@ top_srcdir = ../../../..
 KSFT_KHDR_INSTALL := 1
 UNAME_M := $(shell uname -m)
 
-LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c
+LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/test_util.c
 LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c
 LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c
 LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c
@@ -17,27 +17,33 @@ TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test
 TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid
 TEST_GEN_PROGS_x86_64 += x86_64/mmio_warning_test
 TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test
+TEST_GEN_PROGS_x86_64 += x86_64/set_memory_region_test
 TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test
 TEST_GEN_PROGS_x86_64 += x86_64/smm_test
 TEST_GEN_PROGS_x86_64 += x86_64/state_test
+TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test
 TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_dirty_log_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test
 TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test
-TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test
 TEST_GEN_PROGS_x86_64 += clear_dirty_log_test
+TEST_GEN_PROGS_x86_64 += demand_paging_test
 TEST_GEN_PROGS_x86_64 += dirty_log_test
 TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus
+TEST_GEN_PROGS_x86_64 += steal_time
 
 TEST_GEN_PROGS_aarch64 += clear_dirty_log_test
+TEST_GEN_PROGS_aarch64 += demand_paging_test
 TEST_GEN_PROGS_aarch64 += dirty_log_test
 TEST_GEN_PROGS_aarch64 += kvm_create_max_vcpus
+TEST_GEN_PROGS_aarch64 += steal_time
 
 TEST_GEN_PROGS_s390x = s390x/memop
-TEST_GEN_PROGS_s390x += s390x/sync_regs_test
 TEST_GEN_PROGS_s390x += s390x/resets
+TEST_GEN_PROGS_s390x += s390x/sync_regs_test
+TEST_GEN_PROGS_s390x += demand_paging_test
 TEST_GEN_PROGS_s390x += dirty_log_test
 TEST_GEN_PROGS_s390x += kvm_create_max_vcpus
 
diff --git a/tools/testing/selftests/kvm/clear_dirty_log_test.c b/tools/testing/selftests/kvm/clear_dirty_log_test.c
index 749336937d37..11672ec6f74e 100644
--- a/tools/testing/selftests/kvm/clear_dirty_log_test.c
+++ b/tools/testing/selftests/kvm/clear_dirty_log_test.c
@@ -1,2 +1,6 @@
 #define USE_CLEAR_DIRTY_LOG
+#define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0)
+#define KVM_DIRTY_LOG_INITIALLY_SET         (1 << 1)
+#define KVM_DIRTY_LOG_MANUAL_CAPS   (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
+		KVM_DIRTY_LOG_INITIALLY_SET)
 #include "dirty_log_test.c"
diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
new file mode 100644
index 000000000000..360cd3ea4cd6
--- /dev/null
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -0,0 +1,661 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KVM demand paging test
+ * Adapted from dirty_log_test.c
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ * Copyright (C) 2019, Google, Inc.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_name */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+#include <asm/unistd.h>
+#include <time.h>
+#include <poll.h>
+#include <pthread.h>
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+#include <linux/userfaultfd.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+#ifdef __NR_userfaultfd
+
+/* The memory slot index demand page */
+#define TEST_MEM_SLOT_INDEX		1
+
+/* Default guest test virtual memory offset */
+#define DEFAULT_GUEST_TEST_MEM		0xc0000000
+
+#define DEFAULT_GUEST_TEST_MEM_SIZE (1 << 30) /* 1G */
+
+#ifdef PRINT_PER_PAGE_UPDATES
+#define PER_PAGE_DEBUG(...) printf(__VA_ARGS__)
+#else
+#define PER_PAGE_DEBUG(...) _no_printf(__VA_ARGS__)
+#endif
+
+#ifdef PRINT_PER_VCPU_UPDATES
+#define PER_VCPU_DEBUG(...) printf(__VA_ARGS__)
+#else
+#define PER_VCPU_DEBUG(...) _no_printf(__VA_ARGS__)
+#endif
+
+#define MAX_VCPUS 512
+
+/*
+ * Guest/Host shared variables. Ensure addr_gva2hva() and/or
+ * sync_global_to/from_guest() are used when accessing from
+ * the host. READ/WRITE_ONCE() should also be used with anything
+ * that may change.
+ */
+static uint64_t host_page_size;
+static uint64_t guest_page_size;
+
+static char *guest_data_prototype;
+
+/*
+ * Guest physical memory offset of the testing memory slot.
+ * This will be set to the topmost valid physical address minus
+ * the test memory size.
+ */
+static uint64_t guest_test_phys_mem;
+
+/*
+ * Guest virtual memory offset of the testing memory slot.
+ * Must not conflict with identity mapped test code.
+ */
+static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM;
+
+struct vcpu_args {
+	uint64_t gva;
+	uint64_t pages;
+
+	/* Only used by the host userspace part of the vCPU thread */
+	int vcpu_id;
+	struct kvm_vm *vm;
+};
+
+static struct vcpu_args vcpu_args[MAX_VCPUS];
+
+/*
+ * Continuously write to the first 8 bytes of each page in the demand paging
+ * memory region.
+ */
+static void guest_code(uint32_t vcpu_id)
+{
+	uint64_t gva;
+	uint64_t pages;
+	int i;
+
+	/* Make sure vCPU args data structure is not corrupt. */
+	GUEST_ASSERT(vcpu_args[vcpu_id].vcpu_id == vcpu_id);
+
+	gva = vcpu_args[vcpu_id].gva;
+	pages = vcpu_args[vcpu_id].pages;
+
+	for (i = 0; i < pages; i++) {
+		uint64_t addr = gva + (i * guest_page_size);
+
+		addr &= ~(host_page_size - 1);
+		*(uint64_t *)addr = 0x0123456789ABCDEF;
+	}
+
+	GUEST_SYNC(1);
+}
+
+static void *vcpu_worker(void *data)
+{
+	int ret;
+	struct vcpu_args *args = (struct vcpu_args *)data;
+	struct kvm_vm *vm = args->vm;
+	int vcpu_id = args->vcpu_id;
+	struct kvm_run *run;
+	struct timespec start, end, ts_diff;
+
+	vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
+	run = vcpu_state(vm, vcpu_id);
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+
+	/* Let the guest access its memory */
+	ret = _vcpu_run(vm, vcpu_id);
+	TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret);
+	if (get_ucall(vm, vcpu_id, NULL) != UCALL_SYNC) {
+		TEST_ASSERT(false,
+			    "Invalid guest sync status: exit_reason=%s\n",
+			    exit_reason_str(run->exit_reason));
+	}
+
+	clock_gettime(CLOCK_MONOTONIC, &end);
+	ts_diff = timespec_sub(end, start);
+	PER_VCPU_DEBUG("vCPU %d execution time: %ld.%.9lds\n", vcpu_id,
+		       ts_diff.tv_sec, ts_diff.tv_nsec);
+
+	return NULL;
+}
+
+#define PAGE_SHIFT_4K  12
+#define PTES_PER_4K_PT 512
+
+static struct kvm_vm *create_vm(enum vm_guest_mode mode, int vcpus,
+				uint64_t vcpu_memory_bytes)
+{
+	struct kvm_vm *vm;
+	uint64_t pages = DEFAULT_GUEST_PHY_PAGES;
+
+	/* Account for a few pages per-vCPU for stacks */
+	pages += DEFAULT_STACK_PGS * vcpus;
+
+	/*
+	 * Reserve twice the ammount of memory needed to map the test region and
+	 * the page table / stacks region, at 4k, for page tables. Do the
+	 * calculation with 4K page size: the smallest of all archs. (e.g., 64K
+	 * page size guest will need even less memory for page tables).
+	 */
+	pages += (2 * pages) / PTES_PER_4K_PT;
+	pages += ((2 * vcpus * vcpu_memory_bytes) >> PAGE_SHIFT_4K) /
+		 PTES_PER_4K_PT;
+	pages = vm_adjust_num_guest_pages(mode, pages);
+
+	pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
+
+	vm = _vm_create(mode, pages, O_RDWR);
+	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
+#ifdef __x86_64__
+	vm_create_irqchip(vm);
+#endif
+	return vm;
+}
+
+static int handle_uffd_page_request(int uffd, uint64_t addr)
+{
+	pid_t tid;
+	struct timespec start;
+	struct timespec end;
+	struct uffdio_copy copy;
+	int r;
+
+	tid = syscall(__NR_gettid);
+
+	copy.src = (uint64_t)guest_data_prototype;
+	copy.dst = addr;
+	copy.len = host_page_size;
+	copy.mode = 0;
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+
+	r = ioctl(uffd, UFFDIO_COPY, &copy);
+	if (r == -1) {
+		pr_info("Failed Paged in 0x%lx from thread %d with errno: %d\n",
+			addr, tid, errno);
+		return r;
+	}
+
+	clock_gettime(CLOCK_MONOTONIC, &end);
+
+	PER_PAGE_DEBUG("UFFDIO_COPY %d \t%ld ns\n", tid,
+		       timespec_to_ns(timespec_sub(end, start)));
+	PER_PAGE_DEBUG("Paged in %ld bytes at 0x%lx from thread %d\n",
+		       host_page_size, addr, tid);
+
+	return 0;
+}
+
+bool quit_uffd_thread;
+
+struct uffd_handler_args {
+	int uffd;
+	int pipefd;
+	useconds_t delay;
+};
+
+static void *uffd_handler_thread_fn(void *arg)
+{
+	struct uffd_handler_args *uffd_args = (struct uffd_handler_args *)arg;
+	int uffd = uffd_args->uffd;
+	int pipefd = uffd_args->pipefd;
+	useconds_t delay = uffd_args->delay;
+	int64_t pages = 0;
+	struct timespec start, end, ts_diff;
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+	while (!quit_uffd_thread) {
+		struct uffd_msg msg;
+		struct pollfd pollfd[2];
+		char tmp_chr;
+		int r;
+		uint64_t addr;
+
+		pollfd[0].fd = uffd;
+		pollfd[0].events = POLLIN;
+		pollfd[1].fd = pipefd;
+		pollfd[1].events = POLLIN;
+
+		r = poll(pollfd, 2, -1);
+		switch (r) {
+		case -1:
+			pr_info("poll err");
+			continue;
+		case 0:
+			continue;
+		case 1:
+			break;
+		default:
+			pr_info("Polling uffd returned %d", r);
+			return NULL;
+		}
+
+		if (pollfd[0].revents & POLLERR) {
+			pr_info("uffd revents has POLLERR");
+			return NULL;
+		}
+
+		if (pollfd[1].revents & POLLIN) {
+			r = read(pollfd[1].fd, &tmp_chr, 1);
+			TEST_ASSERT(r == 1,
+				    "Error reading pipefd in UFFD thread\n");
+			return NULL;
+		}
+
+		if (!pollfd[0].revents & POLLIN)
+			continue;
+
+		r = read(uffd, &msg, sizeof(msg));
+		if (r == -1) {
+			if (errno == EAGAIN)
+				continue;
+			pr_info("Read of uffd gor errno %d", errno);
+			return NULL;
+		}
+
+		if (r != sizeof(msg)) {
+			pr_info("Read on uffd returned unexpected size: %d bytes", r);
+			return NULL;
+		}
+
+		if (!(msg.event & UFFD_EVENT_PAGEFAULT))
+			continue;
+
+		if (delay)
+			usleep(delay);
+		addr =  msg.arg.pagefault.address;
+		r = handle_uffd_page_request(uffd, addr);
+		if (r < 0)
+			return NULL;
+		pages++;
+	}
+
+	clock_gettime(CLOCK_MONOTONIC, &end);
+	ts_diff = timespec_sub(end, start);
+	PER_VCPU_DEBUG("userfaulted %ld pages over %ld.%.9lds. (%f/sec)\n",
+		       pages, ts_diff.tv_sec, ts_diff.tv_nsec,
+		       pages / ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0));
+
+	return NULL;
+}
+
+static int setup_demand_paging(struct kvm_vm *vm,
+			       pthread_t *uffd_handler_thread, int pipefd,
+			       useconds_t uffd_delay,
+			       struct uffd_handler_args *uffd_args,
+			       void *hva, uint64_t len)
+{
+	int uffd;
+	struct uffdio_api uffdio_api;
+	struct uffdio_register uffdio_register;
+
+	uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
+	if (uffd == -1) {
+		pr_info("uffd creation failed\n");
+		return -1;
+	}
+
+	uffdio_api.api = UFFD_API;
+	uffdio_api.features = 0;
+	if (ioctl(uffd, UFFDIO_API, &uffdio_api) == -1) {
+		pr_info("ioctl uffdio_api failed\n");
+		return -1;
+	}
+
+	uffdio_register.range.start = (uint64_t)hva;
+	uffdio_register.range.len = len;
+	uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING;
+	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) == -1) {
+		pr_info("ioctl uffdio_register failed\n");
+		return -1;
+	}
+
+	if ((uffdio_register.ioctls & UFFD_API_RANGE_IOCTLS) !=
+			UFFD_API_RANGE_IOCTLS) {
+		pr_info("unexpected userfaultfd ioctl set\n");
+		return -1;
+	}
+
+	uffd_args->uffd = uffd;
+	uffd_args->pipefd = pipefd;
+	uffd_args->delay = uffd_delay;
+	pthread_create(uffd_handler_thread, NULL, uffd_handler_thread_fn,
+		       uffd_args);
+
+	PER_VCPU_DEBUG("Created uffd thread for HVA range [%p, %p)\n",
+		       hva, hva + len);
+
+	return 0;
+}
+
+static void run_test(enum vm_guest_mode mode, bool use_uffd,
+		     useconds_t uffd_delay, int vcpus,
+		     uint64_t vcpu_memory_bytes)
+{
+	pthread_t *vcpu_threads;
+	pthread_t *uffd_handler_threads = NULL;
+	struct uffd_handler_args *uffd_args = NULL;
+	struct timespec start, end, ts_diff;
+	int *pipefds = NULL;
+	struct kvm_vm *vm;
+	uint64_t guest_num_pages;
+	int vcpu_id;
+	int r;
+
+	vm = create_vm(mode, vcpus, vcpu_memory_bytes);
+
+	guest_page_size = vm_get_page_size(vm);
+
+	TEST_ASSERT(vcpu_memory_bytes % guest_page_size == 0,
+		    "Guest memory size is not guest page size aligned.");
+
+	guest_num_pages = (vcpus * vcpu_memory_bytes) / guest_page_size;
+	guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
+
+	/*
+	 * If there should be more memory in the guest test region than there
+	 * can be pages in the guest, it will definitely cause problems.
+	 */
+	TEST_ASSERT(guest_num_pages < vm_get_max_gfn(vm),
+		    "Requested more guest memory than address space allows.\n"
+		    "    guest pages: %lx max gfn: %x vcpus: %d wss: %lx]\n",
+		    guest_num_pages, vm_get_max_gfn(vm), vcpus,
+		    vcpu_memory_bytes);
+
+	host_page_size = getpagesize();
+	TEST_ASSERT(vcpu_memory_bytes % host_page_size == 0,
+		    "Guest memory size is not host page size aligned.");
+
+	guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) *
+			      guest_page_size;
+	guest_test_phys_mem &= ~(host_page_size - 1);
+
+#ifdef __s390x__
+	/* Align to 1M (segment size) */
+	guest_test_phys_mem &= ~((1 << 20) - 1);
+#endif
+
+	pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
+
+	/* Add an extra memory slot for testing demand paging */
+	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+				    guest_test_phys_mem,
+				    TEST_MEM_SLOT_INDEX,
+				    guest_num_pages, 0);
+
+	/* Do mapping for the demand paging memory slot */
+	virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages, 0);
+
+	ucall_init(vm, NULL);
+
+	guest_data_prototype = malloc(host_page_size);
+	TEST_ASSERT(guest_data_prototype,
+		    "Failed to allocate buffer for guest data pattern");
+	memset(guest_data_prototype, 0xAB, host_page_size);
+
+	vcpu_threads = malloc(vcpus * sizeof(*vcpu_threads));
+	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
+
+	if (use_uffd) {
+		uffd_handler_threads =
+			malloc(vcpus * sizeof(*uffd_handler_threads));
+		TEST_ASSERT(uffd_handler_threads, "Memory allocation failed");
+
+		uffd_args = malloc(vcpus * sizeof(*uffd_args));
+		TEST_ASSERT(uffd_args, "Memory allocation failed");
+
+		pipefds = malloc(sizeof(int) * vcpus * 2);
+		TEST_ASSERT(pipefds, "Unable to allocate memory for pipefd");
+	}
+
+	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+		vm_paddr_t vcpu_gpa;
+		void *vcpu_hva;
+
+		vm_vcpu_add_default(vm, vcpu_id, guest_code);
+
+		vcpu_gpa = guest_test_phys_mem + (vcpu_id * vcpu_memory_bytes);
+		PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n",
+			       vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_memory_bytes);
+
+		/* Cache the HVA pointer of the region */
+		vcpu_hva = addr_gpa2hva(vm, vcpu_gpa);
+
+		if (use_uffd) {
+			/*
+			 * Set up user fault fd to handle demand paging
+			 * requests.
+			 */
+			r = pipe2(&pipefds[vcpu_id * 2],
+				  O_CLOEXEC | O_NONBLOCK);
+			TEST_ASSERT(!r, "Failed to set up pipefd");
+
+			r = setup_demand_paging(vm,
+						&uffd_handler_threads[vcpu_id],
+						pipefds[vcpu_id * 2],
+						uffd_delay, &uffd_args[vcpu_id],
+						vcpu_hva, vcpu_memory_bytes);
+			if (r < 0)
+				exit(-r);
+		}
+
+#ifdef __x86_64__
+		vcpu_set_cpuid(vm, vcpu_id, kvm_get_supported_cpuid());
+#endif
+
+		vcpu_args[vcpu_id].vm = vm;
+		vcpu_args[vcpu_id].vcpu_id = vcpu_id;
+		vcpu_args[vcpu_id].gva = guest_test_virt_mem +
+					 (vcpu_id * vcpu_memory_bytes);
+		vcpu_args[vcpu_id].pages = vcpu_memory_bytes / guest_page_size;
+	}
+
+	/* Export the shared variables to the guest */
+	sync_global_to_guest(vm, host_page_size);
+	sync_global_to_guest(vm, guest_page_size);
+	sync_global_to_guest(vm, vcpu_args);
+
+	pr_info("Finished creating vCPUs and starting uffd threads\n");
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+
+	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+		pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker,
+			       &vcpu_args[vcpu_id]);
+	}
+
+	pr_info("Started all vCPUs\n");
+
+	/* Wait for the vcpu threads to quit */
+	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+		pthread_join(vcpu_threads[vcpu_id], NULL);
+		PER_VCPU_DEBUG("Joined thread for vCPU %d\n", vcpu_id);
+	}
+
+	pr_info("All vCPU threads joined\n");
+
+	clock_gettime(CLOCK_MONOTONIC, &end);
+
+	if (use_uffd) {
+		char c;
+
+		/* Tell the user fault fd handler threads to quit */
+		for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+			r = write(pipefds[vcpu_id * 2 + 1], &c, 1);
+			TEST_ASSERT(r == 1, "Unable to write to pipefd");
+
+			pthread_join(uffd_handler_threads[vcpu_id], NULL);
+		}
+	}
+
+	ts_diff = timespec_sub(end, start);
+	pr_info("Total guest execution time: %ld.%.9lds\n",
+		ts_diff.tv_sec, ts_diff.tv_nsec);
+	pr_info("Overall demand paging rate: %f pgs/sec\n",
+		guest_num_pages / ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0));
+
+	ucall_uninit(vm);
+	kvm_vm_free(vm);
+
+	free(guest_data_prototype);
+	free(vcpu_threads);
+	if (use_uffd) {
+		free(uffd_handler_threads);
+		free(uffd_args);
+		free(pipefds);
+	}
+}
+
+struct guest_mode {
+	bool supported;
+	bool enabled;
+};
+static struct guest_mode guest_modes[NUM_VM_MODES];
+
+#define guest_mode_init(mode, supported, enabled) ({ \
+	guest_modes[mode] = (struct guest_mode){ supported, enabled }; \
+})
+
+static void help(char *name)
+{
+	int i;
+
+	puts("");
+	printf("usage: %s [-h] [-m mode] [-u] [-d uffd_delay_usec]\n"
+	       "          [-b memory] [-v vcpus]\n", name);
+	printf(" -m: specify the guest mode ID to test\n"
+	       "     (default: test all supported modes)\n"
+	       "     This option may be used multiple times.\n"
+	       "     Guest mode IDs:\n");
+	for (i = 0; i < NUM_VM_MODES; ++i) {
+		printf("         %d:    %s%s\n", i, vm_guest_mode_string(i),
+		       guest_modes[i].supported ? " (supported)" : "");
+	}
+	printf(" -u: use User Fault FD to handle vCPU page\n"
+	       "     faults.\n");
+	printf(" -d: add a delay in usec to the User Fault\n"
+	       "     FD handler to simulate demand paging\n"
+	       "     overheads. Ignored without -u.\n");
+	printf(" -b: specify the size of the memory region which should be\n"
+	       "     demand paged by each vCPU. e.g. 10M or 3G.\n"
+	       "     Default: 1G\n");
+	printf(" -v: specify the number of vCPUs to run.\n");
+	puts("");
+	exit(0);
+}
+
+int main(int argc, char *argv[])
+{
+	bool mode_selected = false;
+	uint64_t vcpu_memory_bytes = DEFAULT_GUEST_TEST_MEM_SIZE;
+	int vcpus = 1;
+	unsigned int mode;
+	int opt, i;
+	bool use_uffd = false;
+	useconds_t uffd_delay = 0;
+
+#ifdef __x86_64__
+	guest_mode_init(VM_MODE_PXXV48_4K, true, true);
+#endif
+#ifdef __aarch64__
+	guest_mode_init(VM_MODE_P40V48_4K, true, true);
+	guest_mode_init(VM_MODE_P40V48_64K, true, true);
+	{
+		unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE);
+
+		if (limit >= 52)
+			guest_mode_init(VM_MODE_P52V48_64K, true, true);
+		if (limit >= 48) {
+			guest_mode_init(VM_MODE_P48V48_4K, true, true);
+			guest_mode_init(VM_MODE_P48V48_64K, true, true);
+		}
+	}
+#endif
+#ifdef __s390x__
+	guest_mode_init(VM_MODE_P40V48_4K, true, true);
+#endif
+
+	while ((opt = getopt(argc, argv, "hm:ud:b:v:")) != -1) {
+		switch (opt) {
+		case 'm':
+			if (!mode_selected) {
+				for (i = 0; i < NUM_VM_MODES; ++i)
+					guest_modes[i].enabled = false;
+				mode_selected = true;
+			}
+			mode = strtoul(optarg, NULL, 10);
+			TEST_ASSERT(mode < NUM_VM_MODES,
+				    "Guest mode ID %d too big", mode);
+			guest_modes[mode].enabled = true;
+			break;
+		case 'u':
+			use_uffd = true;
+			break;
+		case 'd':
+			uffd_delay = strtoul(optarg, NULL, 0);
+			TEST_ASSERT(uffd_delay >= 0,
+				    "A negative UFFD delay is not supported.");
+			break;
+		case 'b':
+			vcpu_memory_bytes = parse_size(optarg);
+			break;
+		case 'v':
+			vcpus = atoi(optarg);
+			TEST_ASSERT(vcpus > 0,
+				    "Must have a positive number of vCPUs");
+			TEST_ASSERT(vcpus <= MAX_VCPUS,
+				    "This test does not currently support\n"
+				    "more than %d vCPUs.", MAX_VCPUS);
+			break;
+		case 'h':
+		default:
+			help(argv[0]);
+			break;
+		}
+	}
+
+	for (i = 0; i < NUM_VM_MODES; ++i) {
+		if (!guest_modes[i].enabled)
+			continue;
+		TEST_ASSERT(guest_modes[i].supported,
+			    "Guest mode ID %d (%s) not supported.",
+			    i, vm_guest_mode_string(i));
+		run_test(i, use_uffd, uffd_delay, vcpus, vcpu_memory_bytes);
+	}
+
+	return 0;
+}
+
+#else /* __NR_userfaultfd */
+
+#warning "missing __NR_userfaultfd definition"
+
+int main(void)
+{
+	print_skip("__NR_userfaultfd must be present for userfaultfd test");
+	return KSFT_SKIP;
+}
+
+#endif /* __NR_userfaultfd */
diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 5614222a6628..752ec158ac59 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -166,24 +166,22 @@ static void *vcpu_worker(void *data)
 			pages_count += TEST_PAGES_PER_LOOP;
 			generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
 		} else {
-			TEST_ASSERT(false,
-				    "Invalid guest sync status: "
-				    "exit_reason=%s\n",
-				    exit_reason_str(run->exit_reason));
+			TEST_FAIL("Invalid guest sync status: "
+				  "exit_reason=%s\n",
+				  exit_reason_str(run->exit_reason));
 		}
 	}
 
-	DEBUG("Dirtied %"PRIu64" pages\n", pages_count);
+	pr_info("Dirtied %"PRIu64" pages\n", pages_count);
 
 	return NULL;
 }
 
-static void vm_dirty_log_verify(unsigned long *bmap)
+static void vm_dirty_log_verify(enum vm_guest_mode mode, unsigned long *bmap)
 {
+	uint64_t step = vm_num_host_pages(mode, 1);
 	uint64_t page;
 	uint64_t *value_ptr;
-	uint64_t step = host_page_size >= guest_page_size ? 1 :
-				guest_page_size / host_page_size;
 
 	for (page = 0; page < host_num_pages; page += step) {
 		value_ptr = host_test_mem + page * host_page_size;
@@ -252,6 +250,8 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid,
 	struct kvm_vm *vm;
 	uint64_t extra_pg_pages = extra_mem_pages / 512 * 2;
 
+	pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
+
 	vm = _vm_create(mode, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
 	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
 #ifdef __x86_64__
@@ -264,6 +264,10 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid,
 #define DIRTY_MEM_BITS 30 /* 1G */
 #define PAGE_SHIFT_4K  12
 
+#ifdef USE_CLEAR_DIRTY_LOG
+static u64 dirty_log_manual_caps;
+#endif
+
 static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 		     unsigned long interval, uint64_t phys_offset)
 {
@@ -289,14 +293,11 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 	 * case where the size is not aligned to 64 pages.
 	 */
 	guest_num_pages = (1ul << (DIRTY_MEM_BITS -
-				   vm_get_page_shift(vm))) + 16;
-#ifdef __s390x__
-	/* Round up to multiple of 1M (segment size) */
-	guest_num_pages = (guest_num_pages + 0xff) & ~0xffUL;
-#endif
+				   vm_get_page_shift(vm))) + 3;
+	guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
+
 	host_page_size = getpagesize();
-	host_num_pages = (guest_num_pages * guest_page_size) / host_page_size +
-			 !!((guest_num_pages * guest_page_size) % host_page_size);
+	host_num_pages = vm_num_host_pages(mode, guest_num_pages);
 
 	if (!phys_offset) {
 		guest_test_phys_mem = (vm_get_max_gfn(vm) -
@@ -311,7 +312,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 	guest_test_phys_mem &= ~((1 << 20) - 1);
 #endif
 
-	DEBUG("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
+	pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
 
 	bmap = bitmap_alloc(host_num_pages);
 	host_bmap_track = bitmap_alloc(host_num_pages);
@@ -320,7 +321,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 	struct kvm_enable_cap cap = {};
 
 	cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2;
-	cap.args[0] = 1;
+	cap.args[0] = dirty_log_manual_caps;
 	vm_enable_cap(vm, &cap);
 #endif
 
@@ -332,8 +333,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 				    KVM_MEM_LOG_DIRTY_PAGES);
 
 	/* Do mapping for the dirty track memory slot */
-	virt_map(vm, guest_test_virt_mem, guest_test_phys_mem,
-		 guest_num_pages * guest_page_size, 0);
+	virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages, 0);
 
 	/* Cache the HVA pointer of the region */
 	host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)guest_test_phys_mem);
@@ -341,9 +341,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 #ifdef __x86_64__
 	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
 #endif
-#ifdef __aarch64__
 	ucall_init(vm, NULL);
-#endif
 
 	/* Export the shared variables to the guest */
 	sync_global_to_guest(vm, host_page_size);
@@ -369,7 +367,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 		kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0,
 				       host_num_pages);
 #endif
-		vm_dirty_log_verify(bmap);
+		vm_dirty_log_verify(mode, bmap);
 		iteration++;
 		sync_global_to_guest(vm, iteration);
 	}
@@ -378,9 +376,9 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 	host_quit = true;
 	pthread_join(vcpu_thread, NULL);
 
-	DEBUG("Total bits checked: dirty (%"PRIu64"), clear (%"PRIu64"), "
-	      "track_next (%"PRIu64")\n", host_dirty_count, host_clear_count,
-	      host_track_next_count);
+	pr_info("Total bits checked: dirty (%"PRIu64"), clear (%"PRIu64"), "
+		"track_next (%"PRIu64")\n", host_dirty_count, host_clear_count,
+		host_track_next_count);
 
 	free(bmap);
 	free(host_bmap_track);
@@ -388,15 +386,14 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 	kvm_vm_free(vm);
 }
 
-struct vm_guest_mode_params {
+struct guest_mode {
 	bool supported;
 	bool enabled;
 };
-struct vm_guest_mode_params vm_guest_mode_params[NUM_VM_MODES];
+static struct guest_mode guest_modes[NUM_VM_MODES];
 
-#define vm_guest_mode_params_init(mode, supported, enabled)					\
-({												\
-	vm_guest_mode_params[mode] = (struct vm_guest_mode_params){ supported, enabled };	\
+#define guest_mode_init(mode, supported, enabled) ({ \
+	guest_modes[mode] = (struct guest_mode){ supported, enabled }; \
 })
 
 static void help(char *name)
@@ -419,7 +416,7 @@ static void help(char *name)
 	       "     Guest mode IDs:\n");
 	for (i = 0; i < NUM_VM_MODES; ++i) {
 		printf("         %d:    %s%s\n", i, vm_guest_mode_string(i),
-		       vm_guest_mode_params[i].supported ? " (supported)" : "");
+		       guest_modes[i].supported ? " (supported)" : "");
 	}
 	puts("");
 	exit(0);
@@ -433,34 +430,38 @@ int main(int argc, char *argv[])
 	uint64_t phys_offset = 0;
 	unsigned int mode;
 	int opt, i;
-#ifdef __aarch64__
-	unsigned int host_ipa_limit;
-#endif
 
 #ifdef USE_CLEAR_DIRTY_LOG
-	if (!kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2)) {
-		fprintf(stderr, "KVM_CLEAR_DIRTY_LOG not available, skipping tests\n");
+	dirty_log_manual_caps =
+		kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2);
+	if (!dirty_log_manual_caps) {
+		print_skip("KVM_CLEAR_DIRTY_LOG not available");
 		exit(KSFT_SKIP);
 	}
+	dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE |
+				  KVM_DIRTY_LOG_INITIALLY_SET);
 #endif
 
 #ifdef __x86_64__
-	vm_guest_mode_params_init(VM_MODE_PXXV48_4K, true, true);
+	guest_mode_init(VM_MODE_PXXV48_4K, true, true);
 #endif
 #ifdef __aarch64__
-	vm_guest_mode_params_init(VM_MODE_P40V48_4K, true, true);
-	vm_guest_mode_params_init(VM_MODE_P40V48_64K, true, true);
-
-	host_ipa_limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE);
-	if (host_ipa_limit >= 52)
-		vm_guest_mode_params_init(VM_MODE_P52V48_64K, true, true);
-	if (host_ipa_limit >= 48) {
-		vm_guest_mode_params_init(VM_MODE_P48V48_4K, true, true);
-		vm_guest_mode_params_init(VM_MODE_P48V48_64K, true, true);
+	guest_mode_init(VM_MODE_P40V48_4K, true, true);
+	guest_mode_init(VM_MODE_P40V48_64K, true, true);
+
+	{
+		unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE);
+
+		if (limit >= 52)
+			guest_mode_init(VM_MODE_P52V48_64K, true, true);
+		if (limit >= 48) {
+			guest_mode_init(VM_MODE_P48V48_4K, true, true);
+			guest_mode_init(VM_MODE_P48V48_64K, true, true);
+		}
 	}
 #endif
 #ifdef __s390x__
-	vm_guest_mode_params_init(VM_MODE_P40V48_4K, true, true);
+	guest_mode_init(VM_MODE_P40V48_4K, true, true);
 #endif
 
 	while ((opt = getopt(argc, argv, "hi:I:p:m:")) != -1) {
@@ -477,13 +478,13 @@ int main(int argc, char *argv[])
 		case 'm':
 			if (!mode_selected) {
 				for (i = 0; i < NUM_VM_MODES; ++i)
-					vm_guest_mode_params[i].enabled = false;
+					guest_modes[i].enabled = false;
 				mode_selected = true;
 			}
 			mode = strtoul(optarg, NULL, 10);
 			TEST_ASSERT(mode < NUM_VM_MODES,
 				    "Guest mode ID %d too big", mode);
-			vm_guest_mode_params[mode].enabled = true;
+			guest_modes[mode].enabled = true;
 			break;
 		case 'h':
 		default:
@@ -495,15 +496,15 @@ int main(int argc, char *argv[])
 	TEST_ASSERT(iterations > 2, "Iterations must be greater than two");
 	TEST_ASSERT(interval > 0, "Interval must be greater than zero");
 
-	DEBUG("Test iterations: %"PRIu64", interval: %"PRIu64" (ms)\n",
-	      iterations, interval);
+	pr_info("Test iterations: %"PRIu64", interval: %"PRIu64" (ms)\n",
+		iterations, interval);
 
 	srandom(time(0));
 
 	for (i = 0; i < NUM_VM_MODES; ++i) {
-		if (!vm_guest_mode_params[i].enabled)
+		if (!guest_modes[i].enabled)
 			continue;
-		TEST_ASSERT(vm_guest_mode_params[i].supported,
+		TEST_ASSERT(guest_modes[i].supported,
 			    "Guest mode ID %d (%s) not supported.",
 			    i, vm_guest_mode_string(i));
 		run_test(i, iterations, interval, phys_offset);
diff --git a/tools/testing/selftests/kvm/include/evmcs.h b/tools/testing/selftests/kvm/include/evmcs.h
index 4912d23844bc..d8f4d6bfe05d 100644
--- a/tools/testing/selftests/kvm/include/evmcs.h
+++ b/tools/testing/selftests/kvm/include/evmcs.h
@@ -16,6 +16,8 @@
 #define u32 uint32_t
 #define u64 uint64_t
 
+#define EVMCS_VERSION 1
+
 extern bool enable_evmcs;
 
 struct hv_vp_assist_page {
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index ae0d14c2540a..a99b875f50d2 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -16,7 +16,8 @@
 #include "sparsebit.h"
 
 
-/* Callers of kvm_util only have an incomplete/opaque description of the
+/*
+ * Callers of kvm_util only have an incomplete/opaque description of the
  * structure kvm_util is using to maintain the state of a VM.
  */
 struct kvm_vm;
@@ -24,12 +25,6 @@ struct kvm_vm;
 typedef uint64_t vm_paddr_t; /* Virtual Machine (Guest) physical address */
 typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */
 
-#ifndef NDEBUG
-#define DEBUG(...) printf(__VA_ARGS__);
-#else
-#define DEBUG(...)
-#endif
-
 /* Minimum allocated guest virtual and physical addresses */
 #define KVM_UTIL_MIN_VADDR		0x2000
 
@@ -84,6 +79,23 @@ void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename,
 		     uint32_t data_memslot, uint32_t pgd_memslot);
 
 void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent);
+
+/*
+ * VM VCPU Dump
+ *
+ * Input Args:
+ *   stream - Output FILE stream
+ *   vm     - Virtual Machine
+ *   vcpuid - VCPU ID
+ *   indent - Left margin indent amount
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Dumps the current state of the VCPU specified by @vcpuid, within the VM
+ * given by @vm, to the FILE stream given by @stream.
+ */
 void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid,
 	       uint8_t indent);
 
@@ -100,14 +112,31 @@ int _vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl,
 		void *arg);
 void vm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
 void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags);
+void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa);
 void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid);
 vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
 			  uint32_t data_memslot, uint32_t pgd_memslot);
 void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
-	      size_t size, uint32_t pgd_memslot);
+	      unsigned int npages, uint32_t pgd_memslot);
 void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa);
 void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva);
 vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva);
+
+/*
+ * Address Guest Virtual to Guest Physical
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   gva - VM virtual address
+ *
+ * Output Args: None
+ *
+ * Return:
+ *   Equivalent VM physical address
+ *
+ * Returns the VM physical address of the translated VM virtual
+ * address given by @gva.
+ */
 vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva);
 
 struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid);
@@ -118,7 +147,27 @@ void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
 		       struct kvm_mp_state *mp_state);
 void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
 void vcpu_regs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
+
+/*
+ * VM VCPU Args Set
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   vcpuid - VCPU ID
+ *   num - number of arguments
+ *   ... - arguments, each of type uint64_t
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Sets the first @num function input registers of the VCPU with @vcpuid,
+ * per the C calling convention of the architecture, to the values given
+ * as variable args. Each of the variable args is expected to be of type
+ * uint64_t. The maximum @num can be is specific to the architecture.
+ */
 void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...);
+
 void vcpu_sregs_get(struct kvm_vm *vm, uint32_t vcpuid,
 		    struct kvm_sregs *sregs);
 void vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid,
@@ -147,15 +196,57 @@ int vcpu_nested_state_set(struct kvm_vm *vm, uint32_t vcpuid,
 const char *exit_reason_str(unsigned int exit_reason);
 
 void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot);
+
+/*
+ * VM Virtual Page Map
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   vaddr - VM Virtual Address
+ *   paddr - VM Physical Address
+ *   memslot - Memory region slot for new virtual translation tables
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Within @vm, creates a virtual translation for the page starting
+ * at @vaddr to the page starting at @paddr.
+ */
 void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
-		 uint32_t pgd_memslot);
+		 uint32_t memslot);
+
 vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min,
 			     uint32_t memslot);
 vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num,
 			      vm_paddr_t paddr_min, uint32_t memslot);
 
-struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_size,
+/*
+ * Create a VM with reasonable defaults
+ *
+ * Input Args:
+ *   vcpuid - The id of the single VCPU to add to the VM.
+ *   extra_mem_pages - The number of extra pages to add (this will
+ *                     decide how much extra space we will need to
+ *                     setup the page tables using memslot 0)
+ *   guest_code - The vCPU's entry point
+ *
+ * Output Args: None
+ *
+ * Return:
+ *   Pointer to opaque structure that describes the created VM.
+ */
+struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
 				 void *guest_code);
+
+/*
+ * Adds a vCPU with reasonable defaults (e.g. a stack)
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   vcpuid - The id of the VCPU to add to the VM.
+ *   guest_code - The vCPU's entry point
+ */
 void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code);
 
 bool vm_is_unrestricted_guest(struct kvm_vm *vm);
@@ -164,6 +255,21 @@ unsigned int vm_get_page_size(struct kvm_vm *vm);
 unsigned int vm_get_page_shift(struct kvm_vm *vm);
 unsigned int vm_get_max_gfn(struct kvm_vm *vm);
 
+unsigned int vm_calc_num_guest_pages(enum vm_guest_mode mode, size_t size);
+unsigned int vm_num_host_pages(enum vm_guest_mode mode, unsigned int num_guest_pages);
+unsigned int vm_num_guest_pages(enum vm_guest_mode mode, unsigned int num_host_pages);
+static inline unsigned int
+vm_adjust_num_guest_pages(enum vm_guest_mode mode, unsigned int num_guest_pages)
+{
+	unsigned int n;
+	n = vm_num_guest_pages(mode, vm_num_host_pages(mode, num_guest_pages));
+#ifdef __s390x__
+	/* s390 requires 1M aligned guest sizes */
+	n = (n + 255) & ~255;
+#endif
+	return n;
+}
+
 struct kvm_userspace_memory_region *
 kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start,
 				 uint64_t end);
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index a41db6fb7e24..5eb01bf51b86 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -19,12 +19,28 @@
 #include <fcntl.h>
 #include "kselftest.h"
 
+static inline int _no_printf(const char *format, ...) { return 0; }
+
+#ifdef DEBUG
+#define pr_debug(...) printf(__VA_ARGS__)
+#else
+#define pr_debug(...) _no_printf(__VA_ARGS__)
+#endif
+#ifndef QUIET
+#define pr_info(...) printf(__VA_ARGS__)
+#else
+#define pr_info(...) _no_printf(__VA_ARGS__)
+#endif
+
+void print_skip(const char *fmt, ...) __attribute__((format(printf, 1, 2)));
+
 ssize_t test_write(int fd, const void *buf, size_t count);
 ssize_t test_read(int fd, void *buf, size_t count);
 int test_seq_read(const char *path, char **bufp, size_t *sizep);
 
 void test_assert(bool exp, const char *exp_str,
-		 const char *file, unsigned int line, const char *fmt, ...);
+		 const char *file, unsigned int line, const char *fmt, ...)
+		__attribute__((format(printf, 5, 6)));
 
 #define TEST_ASSERT(e, fmt, ...) \
 	test_assert((e), #e, __FILE__, __LINE__, fmt, ##__VA_ARGS__)
@@ -39,4 +55,14 @@ void test_assert(bool exp, const char *exp_str,
 		    #a, #b, #a, (unsigned long) __a, #b, (unsigned long) __b); \
 } while (0)
 
+#define TEST_FAIL(fmt, ...) \
+	TEST_ASSERT(false, fmt, ##__VA_ARGS__)
+
+size_t parse_size(const char *size);
+
+int64_t timespec_to_ns(struct timespec ts);
+struct timespec timespec_add_ns(struct timespec ts, int64_t ns);
+struct timespec timespec_add(struct timespec ts1, struct timespec ts2);
+struct timespec timespec_sub(struct timespec ts1, struct timespec ts2);
+
 #endif /* SELFTEST_KVM_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c
index 6f38c3dc0d56..0299cd81b8ba 100644
--- a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c
+++ b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c
@@ -24,8 +24,8 @@ void test_vcpu_creation(int first_vcpu_id, int num_vcpus)
 	struct kvm_vm *vm;
 	int i;
 
-	printf("Testing creating %d vCPUs, with IDs %d...%d.\n",
-	       num_vcpus, first_vcpu_id, first_vcpu_id + num_vcpus - 1);
+	pr_info("Testing creating %d vCPUs, with IDs %d...%d.\n",
+		num_vcpus, first_vcpu_id, first_vcpu_id + num_vcpus - 1);
 
 	vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
 
@@ -41,8 +41,8 @@ int main(int argc, char *argv[])
 	int kvm_max_vcpu_id = kvm_check_cap(KVM_CAP_MAX_VCPU_ID);
 	int kvm_max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS);
 
-	printf("KVM_CAP_MAX_VCPU_ID: %d\n", kvm_max_vcpu_id);
-	printf("KVM_CAP_MAX_VCPUS: %d\n", kvm_max_vcpus);
+	pr_info("KVM_CAP_MAX_VCPU_ID: %d\n", kvm_max_vcpu_id);
+	pr_info("KVM_CAP_MAX_VCPUS: %d\n", kvm_max_vcpus);
 
 	/*
 	 * Upstream KVM prior to 4.8 does not support KVM_CAP_MAX_VCPU_ID.
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index 86036a59a668..2afa6618b396 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -130,7 +130,7 @@ void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 		ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pte_index(vm, vaddr) * 8;
 		break;
 	default:
-		TEST_ASSERT(false, "Page table levels must be 2, 3, or 4");
+		TEST_FAIL("Page table levels must be 2, 3, or 4");
 	}
 
 	*ptep = paddr | 3;
@@ -173,20 +173,19 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
 			goto unmapped_gva;
 		break;
 	default:
-		TEST_ASSERT(false, "Page table levels must be 2, 3, or 4");
+		TEST_FAIL("Page table levels must be 2, 3, or 4");
 	}
 
 	return pte_addr(vm, *ptep) + (gva & (vm->page_size - 1));
 
 unmapped_gva:
-	TEST_ASSERT(false, "No mapping for vm virtual address, "
-		    "gva: 0x%lx", gva);
+	TEST_FAIL("No mapping for vm virtual address, gva: 0x%lx", gva);
 	exit(1);
 }
 
 static void pte_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent, uint64_t page, int level)
 {
-#ifdef DEBUG_VM
+#ifdef DEBUG
 	static const char * const type[] = { "", "pud", "pmd", "pte" };
 	uint64_t pte, *ptep;
 
@@ -197,7 +196,7 @@ static void pte_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent, uint64_t p
 		ptep = addr_gpa2hva(vm, pte);
 		if (!*ptep)
 			continue;
-		printf("%*s%s: %lx: %lx at %p\n", indent, "", type[level], pte, *ptep, ptep);
+		fprintf(stream, "%*s%s: %lx: %lx at %p\n", indent, "", type[level], pte, *ptep, ptep);
 		pte_dump(stream, vm, indent + 1, pte_addr(vm, *ptep), level + 1);
 	}
 #endif
@@ -215,7 +214,7 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
 		ptep = addr_gpa2hva(vm, pgd);
 		if (!*ptep)
 			continue;
-		printf("%*spgd: %lx: %lx at %p\n", indent, "", pgd, *ptep, ptep);
+		fprintf(stream, "%*spgd: %lx: %lx at %p\n", indent, "", pgd, *ptep, ptep);
 		pte_dump(stream, vm, indent + 1, pte_addr(vm, *ptep), level);
 	}
 }
@@ -262,11 +261,11 @@ void aarch64_vcpu_setup(struct kvm_vm *vm, int vcpuid, struct kvm_vcpu_init *ini
 
 	switch (vm->mode) {
 	case VM_MODE_P52V48_4K:
-		TEST_ASSERT(false, "AArch64 does not support 4K sized pages "
-				   "with 52-bit physical address ranges");
+		TEST_FAIL("AArch64 does not support 4K sized pages "
+			  "with 52-bit physical address ranges");
 	case VM_MODE_PXXV48_4K:
-		TEST_ASSERT(false, "AArch64 does not support 4K sized pages "
-				   "with ANY-bit physical address ranges");
+		TEST_FAIL("AArch64 does not support 4K sized pages "
+			  "with ANY-bit physical address ranges");
 	case VM_MODE_P52V48_64K:
 		tcr_el1 |= 1ul << 14; /* TG0 = 64KB */
 		tcr_el1 |= 6ul << 32; /* IPS = 52 bits */
@@ -288,7 +287,7 @@ void aarch64_vcpu_setup(struct kvm_vm *vm, int vcpuid, struct kvm_vcpu_init *ini
 		tcr_el1 |= 2ul << 32; /* IPS = 40 bits */
 		break;
 	default:
-		TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", vm->mode);
+		TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode);
 	}
 
 	sctlr_el1 |= (1 << 0) | (1 << 2) | (1 << 12) /* M | C | I */;
@@ -333,3 +332,21 @@ void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
 {
 	aarch64_vcpu_add_default(vm, vcpuid, NULL, guest_code);
 }
+
+void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...)
+{
+	va_list ap;
+	int i;
+
+	TEST_ASSERT(num >= 1 && num <= 8, "Unsupported number of args,\n"
+		    "  num: %u\n", num);
+
+	va_start(ap, num);
+
+	for (i = 0; i < num; i++) {
+		set_reg(vm, vcpuid, ARM64_CORE_REG(regs.regs[i]),
+			va_arg(ap, uint64_t));
+	}
+
+	va_end(ap);
+}
diff --git a/tools/testing/selftests/kvm/lib/aarch64/ucall.c b/tools/testing/selftests/kvm/lib/aarch64/ucall.c
index 6cd91970fbad..c8e0ec20d3bf 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/ucall.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/ucall.c
@@ -62,7 +62,7 @@ void ucall_init(struct kvm_vm *vm, void *arg)
 		if (ucall_mmio_init(vm, start + offset))
 			return;
 	}
-	TEST_ASSERT(false, "Can't find a ucall mmio address");
+	TEST_FAIL("Can't find a ucall mmio address");
 }
 
 void ucall_uninit(struct kvm_vm *vm)
diff --git a/tools/testing/selftests/kvm/lib/assert.c b/tools/testing/selftests/kvm/lib/assert.c
index d1cf9f6e0e6b..5ebbd0d6b472 100644
--- a/tools/testing/selftests/kvm/lib/assert.c
+++ b/tools/testing/selftests/kvm/lib/assert.c
@@ -82,8 +82,10 @@ test_assert(bool exp, const char *exp_str,
 		}
 		va_end(ap);
 
-		if (errno == EACCES)
-			ksft_exit_skip("Access denied - Exiting.\n");
+		if (errno == EACCES) {
+			print_skip("Access denied - Exiting");
+			exit(KSFT_SKIP);
+		}
 		exit(254);
 	}
 
diff --git a/tools/testing/selftests/kvm/lib/io.c b/tools/testing/selftests/kvm/lib/io.c
index eaf351cc7e7f..fedb2a741f0b 100644
--- a/tools/testing/selftests/kvm/lib/io.c
+++ b/tools/testing/selftests/kvm/lib/io.c
@@ -61,9 +61,9 @@ ssize_t test_write(int fd, const void *buf, size_t count)
 			continue;
 
 		case 0:
-			TEST_ASSERT(false, "Unexpected EOF,\n"
-				    "  rc: %zi num_written: %zi num_left: %zu",
-				    rc, num_written, num_left);
+			TEST_FAIL("Unexpected EOF,\n"
+				  "  rc: %zi num_written: %zi num_left: %zu",
+				  rc, num_written, num_left);
 			break;
 
 		default:
@@ -138,9 +138,9 @@ ssize_t test_read(int fd, void *buf, size_t count)
 			break;
 
 		case 0:
-			TEST_ASSERT(false, "Unexpected EOF,\n"
-				    "  rc: %zi num_read: %zi num_left: %zu",
-				    rc, num_read, num_left);
+			TEST_FAIL("Unexpected EOF,\n"
+				  "   rc: %zi num_read: %zi num_left: %zu",
+				  rc, num_read, num_left);
 			break;
 
 		default:
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index a6dd0401eb50..8a3523d4434f 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -92,7 +92,7 @@ static void vm_open(struct kvm_vm *vm, int perm)
 		exit(KSFT_SKIP);
 
 	if (!kvm_check_cap(KVM_CAP_IMMEDIATE_EXIT)) {
-		fprintf(stderr, "immediate_exit not available, skipping test\n");
+		print_skip("immediate_exit not available");
 		exit(KSFT_SKIP);
 	}
 
@@ -113,6 +113,25 @@ const char * const vm_guest_mode_string[] = {
 _Static_assert(sizeof(vm_guest_mode_string)/sizeof(char *) == NUM_VM_MODES,
 	       "Missing new mode strings?");
 
+struct vm_guest_mode_params {
+	unsigned int pa_bits;
+	unsigned int va_bits;
+	unsigned int page_size;
+	unsigned int page_shift;
+};
+
+static const struct vm_guest_mode_params vm_guest_mode_params[] = {
+	{ 52, 48,  0x1000, 12 },
+	{ 52, 48, 0x10000, 16 },
+	{ 48, 48,  0x1000, 12 },
+	{ 48, 48, 0x10000, 16 },
+	{ 40, 48,  0x1000, 12 },
+	{ 40, 48, 0x10000, 16 },
+	{  0,  0,  0x1000, 12 },
+};
+_Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES,
+	       "Missing new mode params?");
+
 /*
  * VM Create
  *
@@ -136,7 +155,8 @@ struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 {
 	struct kvm_vm *vm;
 
-	DEBUG("Testing guest mode: %s\n", vm_guest_mode_string(mode));
+	pr_debug("%s: mode='%s' pages='%ld' perm='%d'\n", __func__,
+		 vm_guest_mode_string(mode), phy_pages, perm);
 
 	vm = calloc(1, sizeof(*vm));
 	TEST_ASSERT(vm != NULL, "Insufficient Memory");
@@ -144,67 +164,45 @@ struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 	vm->mode = mode;
 	vm->type = 0;
 
+	vm->pa_bits = vm_guest_mode_params[mode].pa_bits;
+	vm->va_bits = vm_guest_mode_params[mode].va_bits;
+	vm->page_size = vm_guest_mode_params[mode].page_size;
+	vm->page_shift = vm_guest_mode_params[mode].page_shift;
+
 	/* Setup mode specific traits. */
 	switch (vm->mode) {
 	case VM_MODE_P52V48_4K:
 		vm->pgtable_levels = 4;
-		vm->pa_bits = 52;
-		vm->va_bits = 48;
-		vm->page_size = 0x1000;
-		vm->page_shift = 12;
 		break;
 	case VM_MODE_P52V48_64K:
 		vm->pgtable_levels = 3;
-		vm->pa_bits = 52;
-		vm->va_bits = 48;
-		vm->page_size = 0x10000;
-		vm->page_shift = 16;
 		break;
 	case VM_MODE_P48V48_4K:
 		vm->pgtable_levels = 4;
-		vm->pa_bits = 48;
-		vm->va_bits = 48;
-		vm->page_size = 0x1000;
-		vm->page_shift = 12;
 		break;
 	case VM_MODE_P48V48_64K:
 		vm->pgtable_levels = 3;
-		vm->pa_bits = 48;
-		vm->va_bits = 48;
-		vm->page_size = 0x10000;
-		vm->page_shift = 16;
 		break;
 	case VM_MODE_P40V48_4K:
 		vm->pgtable_levels = 4;
-		vm->pa_bits = 40;
-		vm->va_bits = 48;
-		vm->page_size = 0x1000;
-		vm->page_shift = 12;
 		break;
 	case VM_MODE_P40V48_64K:
 		vm->pgtable_levels = 3;
-		vm->pa_bits = 40;
-		vm->va_bits = 48;
-		vm->page_size = 0x10000;
-		vm->page_shift = 16;
 		break;
 	case VM_MODE_PXXV48_4K:
 #ifdef __x86_64__
 		kvm_get_cpu_address_width(&vm->pa_bits, &vm->va_bits);
 		TEST_ASSERT(vm->va_bits == 48, "Linear address width "
 			    "(%d bits) not supported", vm->va_bits);
+		pr_debug("Guest physical address width detected: %d\n",
+			 vm->pa_bits);
 		vm->pgtable_levels = 4;
-		vm->page_size = 0x1000;
-		vm->page_shift = 12;
-		DEBUG("Guest physical address width detected: %d\n",
-		      vm->pa_bits);
 #else
-		TEST_ASSERT(false, "VM_MODE_PXXV48_4K not supported on "
-			    "non-x86 platforms");
+		TEST_FAIL("VM_MODE_PXXV48_4K not supported on non-x86 platforms");
 #endif
 		break;
 	default:
-		TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", mode);
+		TEST_FAIL("Unknown guest mode, mode: 0x%x", mode);
 	}
 
 #ifdef __aarch64__
@@ -266,7 +264,7 @@ void kvm_vm_restart(struct kvm_vm *vmp, int perm)
 		TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n"
 			    "  rc: %i errno: %i\n"
 			    "  slot: %u flags: 0x%x\n"
-			    "  guest_phys_addr: 0x%lx size: 0x%lx",
+			    "  guest_phys_addr: 0x%llx size: 0x%llx",
 			    ret, errno, region->region.slot,
 			    region->region.flags,
 			    region->region.guest_phys_addr,
@@ -281,7 +279,7 @@ void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log)
 
 	ret = ioctl(vm->fd, KVM_GET_DIRTY_LOG, &args);
 	TEST_ASSERT(ret == 0, "%s: KVM_GET_DIRTY_LOG failed: %s",
-		    strerror(-ret));
+		    __func__, strerror(-ret));
 }
 
 void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log,
@@ -294,7 +292,7 @@ void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log,
 
 	ret = ioctl(vm->fd, KVM_CLEAR_DIRTY_LOG, &args);
 	TEST_ASSERT(ret == 0, "%s: KVM_CLEAR_DIRTY_LOG failed: %s",
-		    strerror(-ret));
+		    __func__, strerror(-ret));
 }
 
 /*
@@ -582,6 +580,10 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	size_t huge_page_size = KVM_UTIL_PGS_PER_HUGEPG * vm->page_size;
 	size_t alignment;
 
+	TEST_ASSERT(vm_adjust_num_guest_pages(vm->mode, npages) == npages,
+		"Number of guest pages is not compatible with the host. "
+		"Try npages=%d", vm_adjust_num_guest_pages(vm->mode, npages));
+
 	TEST_ASSERT((guest_paddr % vm->page_size) == 0, "Guest physical "
 		"address not on a page boundary.\n"
 		"  guest_paddr: 0x%lx vm->page_size: 0x%x",
@@ -600,7 +602,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	region = (struct userspace_mem_region *) userspace_mem_region_find(
 		vm, guest_paddr, (guest_paddr + npages * vm->page_size) - 1);
 	if (region != NULL)
-		TEST_ASSERT(false, "overlapping userspace_mem_region already "
+		TEST_FAIL("overlapping userspace_mem_region already "
 			"exists\n"
 			"  requested guest_paddr: 0x%lx npages: 0x%lx "
 			"page_size: 0x%x\n"
@@ -616,7 +618,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 			break;
 	}
 	if (region != NULL)
-		TEST_ASSERT(false, "A mem region with the requested slot "
+		TEST_FAIL("A mem region with the requested slot "
 			"already exists.\n"
 			"  requested slot: %u paddr: 0x%lx npages: 0x%lx\n"
 			"  existing slot: %u paddr: 0x%lx size: 0x%lx",
@@ -720,7 +722,7 @@ memslot2region(struct kvm_vm *vm, uint32_t memslot)
 			"  requested slot: %u\n", memslot);
 		fputs("---- vm dump ----\n", stderr);
 		vm_dump(stderr, vm, 2);
-		TEST_ASSERT(false, "Mem region not found");
+		TEST_FAIL("Mem region not found");
 	}
 
 	return region;
@@ -757,6 +759,36 @@ void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags)
 }
 
 /*
+ * VM Memory Region Move
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   slot - Slot of the memory region to move
+ *   new_gpa - Starting guest physical address
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Change the gpa of a memory region.
+ */
+void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa)
+{
+	struct userspace_mem_region *region;
+	int ret;
+
+	region = memslot2region(vm, slot);
+
+	region->region.guest_phys_addr = new_gpa;
+
+	ret = ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, &region->region);
+
+	TEST_ASSERT(!ret, "KVM_SET_USER_MEMORY_REGION failed\n"
+		    "ret: %i errno: %i slot: %u new_gpa: 0x%lx",
+		    ret, errno, slot, new_gpa);
+}
+
+/*
  * VCPU mmap Size
  *
  * Input Args: None
@@ -808,7 +840,7 @@ void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid)
 	/* Confirm a vcpu with the specified id doesn't already exist. */
 	vcpu = vcpu_find(vm, vcpuid);
 	if (vcpu != NULL)
-		TEST_ASSERT(false, "vcpu with the specified id "
+		TEST_FAIL("vcpu with the specified id "
 			"already exists,\n"
 			"  requested vcpuid: %u\n"
 			"  existing vcpuid: %u state: %p",
@@ -901,8 +933,7 @@ static vm_vaddr_t vm_vaddr_unused_gap(struct kvm_vm *vm, size_t sz,
 	} while (pgidx_start != 0);
 
 no_va_found:
-	TEST_ASSERT(false, "No vaddr of specified pages available, "
-		"pages: 0x%lx", pages);
+	TEST_FAIL("No vaddr of specified pages available, pages: 0x%lx", pages);
 
 	/* NOT REACHED */
 	return -1;
@@ -982,21 +1013,21 @@ vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
  *   vm - Virtual Machine
  *   vaddr - Virtuall address to map
  *   paddr - VM Physical Address
- *   size - The size of the range to map
+ *   npages - The number of pages to map
  *   pgd_memslot - Memory region slot for new virtual translation tables
  *
  * Output Args: None
  *
  * Return: None
  *
- * Within the VM given by vm, creates a virtual translation for the
- * page range starting at vaddr to the page range starting at paddr.
+ * Within the VM given by @vm, creates a virtual translation for
+ * @npages starting at @vaddr to the page range starting at @paddr.
  */
 void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
-	      size_t size, uint32_t pgd_memslot)
+	      unsigned int npages, uint32_t pgd_memslot)
 {
 	size_t page_size = vm->page_size;
-	size_t npages = size / page_size;
+	size_t size = npages * page_size;
 
 	TEST_ASSERT(vaddr + size > vaddr, "Vaddr overflow");
 	TEST_ASSERT(paddr + size > paddr, "Paddr overflow");
@@ -1037,7 +1068,7 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa)
 				+ (gpa - region->region.guest_phys_addr));
 	}
 
-	TEST_ASSERT(false, "No vm physical memory at 0x%lx", gpa);
+	TEST_FAIL("No vm physical memory at 0x%lx", gpa);
 	return NULL;
 }
 
@@ -1071,8 +1102,7 @@ vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva)
 				+ (hva - (uintptr_t) region->host_mem));
 	}
 
-	TEST_ASSERT(false, "No mapping to a guest physical address, "
-		"hva: %p", hva);
+	TEST_FAIL("No mapping to a guest physical address, hva: %p", hva);
 	return -1;
 }
 
@@ -1703,3 +1733,43 @@ unsigned int vm_get_max_gfn(struct kvm_vm *vm)
 {
 	return vm->max_gfn;
 }
+
+static unsigned int vm_calc_num_pages(unsigned int num_pages,
+				      unsigned int page_shift,
+				      unsigned int new_page_shift,
+				      bool ceil)
+{
+	unsigned int n = 1 << (new_page_shift - page_shift);
+
+	if (page_shift >= new_page_shift)
+		return num_pages * (1 << (page_shift - new_page_shift));
+
+	return num_pages / n + !!(ceil && num_pages % n);
+}
+
+static inline int getpageshift(void)
+{
+	return __builtin_ffs(getpagesize()) - 1;
+}
+
+unsigned int
+vm_num_host_pages(enum vm_guest_mode mode, unsigned int num_guest_pages)
+{
+	return vm_calc_num_pages(num_guest_pages,
+				 vm_guest_mode_params[mode].page_shift,
+				 getpageshift(), true);
+}
+
+unsigned int
+vm_num_guest_pages(enum vm_guest_mode mode, unsigned int num_host_pages)
+{
+	return vm_calc_num_pages(num_host_pages, getpageshift(),
+				 vm_guest_mode_params[mode].page_shift, false);
+}
+
+unsigned int vm_calc_num_guest_pages(enum vm_guest_mode mode, size_t size)
+{
+	unsigned int n;
+	n = DIV_ROUND_UP(size, vm_guest_mode_params[mode].page_size);
+	return vm_adjust_num_guest_pages(mode, n);
+}
diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
index ac50c42750cf..ca56a0133127 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h
+++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
@@ -12,17 +12,6 @@
 
 #define KVM_DEV_PATH		"/dev/kvm"
 
-#ifndef BITS_PER_BYTE
-#define BITS_PER_BYTE		8
-#endif
-
-#ifndef BITS_PER_LONG
-#define BITS_PER_LONG		(BITS_PER_BYTE * sizeof(long))
-#endif
-
-#define DIV_ROUND_UP(n, d)	(((n) + (d) - 1) / (d))
-#define BITS_TO_LONGS(nr)	DIV_ROUND_UP(nr, BITS_PER_LONG)
-
 struct userspace_mem_region {
 	struct userspace_mem_region *next, *prev;
 	struct kvm_userspace_memory_region region;
@@ -64,8 +53,56 @@ struct kvm_vm {
 };
 
 struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid);
+
+/*
+ * Virtual Translation Tables Dump
+ *
+ * Input Args:
+ *   stream - Output FILE stream
+ *   vm     - Virtual Machine
+ *   indent - Left margin indent amount
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Dumps to the FILE stream given by @stream, the contents of all the
+ * virtual translation tables for the VM given by @vm.
+ */
 void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent);
+
+/*
+ * Register Dump
+ *
+ * Input Args:
+ *   stream - Output FILE stream
+ *   regs   - Registers
+ *   indent - Left margin indent amount
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Dumps the state of the registers given by @regs, to the FILE stream
+ * given by @stream.
+ */
 void regs_dump(FILE *stream, struct kvm_regs *regs, uint8_t indent);
+
+/*
+ * System Register Dump
+ *
+ * Input Args:
+ *   stream - Output FILE stream
+ *   sregs  - System registers
+ *   indent - Left margin indent amount
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Dumps the state of the system registers given by @sregs, to the FILE stream
+ * given by @stream.
+ */
 void sregs_dump(FILE *stream, struct kvm_sregs *sregs, uint8_t indent);
 
 struct userspace_mem_region *
diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390x/processor.c
index 32a02360b1eb..8d94961bd046 100644
--- a/tools/testing/selftests/kvm/lib/s390x/processor.c
+++ b/tools/testing/selftests/kvm/lib/s390x/processor.c
@@ -51,22 +51,6 @@ static uint64_t virt_alloc_region(struct kvm_vm *vm, int ri, uint32_t memslot)
 		| ((ri < 4 ? (PAGES_PER_REGION - 1) : 0) & REGION_ENTRY_LENGTH);
 }
 
-/*
- * VM Virtual Page Map
- *
- * Input Args:
- *   vm - Virtual Machine
- *   gva - VM Virtual Address
- *   gpa - VM Physical Address
- *   memslot - Memory region slot for new virtual translation tables
- *
- * Output Args: None
- *
- * Return: None
- *
- * Within the VM given by vm, creates a virtual translation for the page
- * starting at vaddr to the page starting at paddr.
- */
 void virt_pg_map(struct kvm_vm *vm, uint64_t gva, uint64_t gpa,
 		 uint32_t memslot)
 {
@@ -107,26 +91,6 @@ void virt_pg_map(struct kvm_vm *vm, uint64_t gva, uint64_t gpa,
 	entry[idx] = gpa;
 }
 
-/*
- * Address Guest Virtual to Guest Physical
- *
- * Input Args:
- *   vm - Virtual Machine
- *   gpa - VM virtual address
- *
- * Output Args: None
- *
- * Return:
- *   Equivalent VM physical address
- *
- * Translates the VM virtual address given by gva to a VM physical
- * address and then locates the memory region containing the VM
- * physical address, within the VM given by vm.  When found, the host
- * virtual address providing the memory to the vm physical address is
- * returned.
- * A TEST_ASSERT failure occurs if no region containing translated
- * VM virtual address exists.
- */
 vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
 {
 	int ri, idx;
@@ -196,21 +160,6 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
 	virt_dump_region(stream, vm, indent, vm->pgd);
 }
 
-/*
- * Create a VM with reasonable defaults
- *
- * Input Args:
- *   vcpuid - The id of the single VCPU to add to the VM.
- *   extra_mem_pages - The size of extra memories to add (this will
- *                     decide how much extra space we will need to
- *                     setup the page tables using mem slot 0)
- *   guest_code - The vCPU's entry point
- *
- * Output Args: None
- *
- * Return:
- *   Pointer to opaque structure that describes the created VM.
- */
 struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
 				 void *guest_code)
 {
@@ -231,13 +180,6 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
 	return vm;
 }
 
-/*
- * Adds a vCPU with reasonable defaults (i.e. a stack and initial PSW)
- *
- * Input Args:
- *   vcpuid - The id of the VCPU to add to the VM.
- *   guest_code - The vCPU's entry point
- */
 void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
 {
 	size_t stack_size =  DEFAULT_STACK_PGS * getpagesize();
@@ -269,6 +211,26 @@ void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
 	run->psw_addr = (uintptr_t)guest_code;
 }
 
+void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...)
+{
+	va_list ap;
+	struct kvm_regs regs;
+	int i;
+
+	TEST_ASSERT(num >= 1 && num <= 5, "Unsupported number of args,\n"
+		    "  num: %u\n",
+		    num);
+
+	va_start(ap, num);
+	vcpu_regs_get(vm, vcpuid, &regs);
+
+	for (i = 0; i < num; i++)
+		regs.gprs[i + 2] = va_arg(ap, uint64_t);
+
+	vcpu_regs_set(vm, vcpuid, &regs);
+	va_end(ap);
+}
+
 void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent)
 {
 	struct vcpu *vcpu = vm->vcpu_head;
diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c
new file mode 100644
index 000000000000..689e97c27ee2
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/test_util.c
@@ -0,0 +1,93 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * tools/testing/selftests/kvm/lib/test_util.c
+ *
+ * Copyright (C) 2020, Google LLC.
+ */
+#include <stdlib.h>
+#include <ctype.h>
+#include <limits.h>
+#include <assert.h>
+#include "test_util.h"
+
+/*
+ * Parses "[0-9]+[kmgt]?".
+ */
+size_t parse_size(const char *size)
+{
+	size_t base;
+	char *scale;
+	int shift = 0;
+
+	TEST_ASSERT(size && isdigit(size[0]), "Need at least one digit in '%s'", size);
+
+	base = strtoull(size, &scale, 0);
+
+	TEST_ASSERT(base != ULLONG_MAX, "Overflow parsing size!");
+
+	switch (tolower(*scale)) {
+	case 't':
+		shift = 40;
+		break;
+	case 'g':
+		shift = 30;
+		break;
+	case 'm':
+		shift = 20;
+		break;
+	case 'k':
+		shift = 10;
+		break;
+	case 'b':
+	case '\0':
+		shift = 0;
+		break;
+	default:
+		TEST_ASSERT(false, "Unknown size letter %c", *scale);
+	}
+
+	TEST_ASSERT((base << shift) >> shift == base, "Overflow scaling size!");
+
+	return base << shift;
+}
+
+int64_t timespec_to_ns(struct timespec ts)
+{
+	return (int64_t)ts.tv_nsec + 1000000000LL * (int64_t)ts.tv_sec;
+}
+
+struct timespec timespec_add_ns(struct timespec ts, int64_t ns)
+{
+	struct timespec res;
+
+	res.tv_nsec = ts.tv_nsec + ns;
+	res.tv_sec = ts.tv_sec + res.tv_nsec / 1000000000LL;
+	res.tv_nsec %= 1000000000LL;
+
+	return res;
+}
+
+struct timespec timespec_add(struct timespec ts1, struct timespec ts2)
+{
+	int64_t ns1 = timespec_to_ns(ts1);
+	int64_t ns2 = timespec_to_ns(ts2);
+	return timespec_add_ns((struct timespec){0}, ns1 + ns2);
+}
+
+struct timespec timespec_sub(struct timespec ts1, struct timespec ts2)
+{
+	int64_t ns1 = timespec_to_ns(ts1);
+	int64_t ns2 = timespec_to_ns(ts2);
+	return timespec_add_ns((struct timespec){0}, ns1 - ns2);
+}
+
+void print_skip(const char *fmt, ...)
+{
+	va_list ap;
+
+	assert(fmt);
+	va_start(ap, fmt);
+	vprintf(fmt, ap);
+	va_end(ap);
+	puts(", skipping test");
+}
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index 683d3bdb8f6a..f6eb34eaa0d2 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -77,20 +77,6 @@ struct pageTableEntry {
 	uint64_t execute_disable:1;
 };
 
-/* Register Dump
- *
- * Input Args:
- *   indent - Left margin indent amount
- *   regs - register
- *
- * Output Args:
- *   stream - Output FILE stream
- *
- * Return: None
- *
- * Dumps the state of the registers given by regs, to the FILE stream
- * given by steam.
- */
 void regs_dump(FILE *stream, struct kvm_regs *regs,
 	       uint8_t indent)
 {
@@ -115,19 +101,20 @@ void regs_dump(FILE *stream, struct kvm_regs *regs,
 		regs->rip, regs->rflags);
 }
 
-/* Segment Dump
+/*
+ * Segment Dump
  *
  * Input Args:
- *   indent - Left margin indent amount
+ *   stream  - Output FILE stream
  *   segment - KVM segment
+ *   indent  - Left margin indent amount
  *
- * Output Args:
- *   stream - Output FILE stream
+ * Output Args: None
  *
  * Return: None
  *
- * Dumps the state of the KVM segment given by segment, to the FILE stream
- * given by steam.
+ * Dumps the state of the KVM segment given by @segment, to the FILE stream
+ * given by @stream.
  */
 static void segment_dump(FILE *stream, struct kvm_segment *segment,
 			 uint8_t indent)
@@ -146,19 +133,20 @@ static void segment_dump(FILE *stream, struct kvm_segment *segment,
 		segment->unusable, segment->padding);
 }
 
-/* dtable Dump
+/*
+ * dtable Dump
  *
  * Input Args:
- *   indent - Left margin indent amount
+ *   stream - Output FILE stream
  *   dtable - KVM dtable
+ *   indent - Left margin indent amount
  *
- * Output Args:
- *   stream - Output FILE stream
+ * Output Args: None
  *
  * Return: None
  *
- * Dumps the state of the KVM dtable given by dtable, to the FILE stream
- * given by steam.
+ * Dumps the state of the KVM dtable given by @dtable, to the FILE stream
+ * given by @stream.
  */
 static void dtable_dump(FILE *stream, struct kvm_dtable *dtable,
 			uint8_t indent)
@@ -169,20 +157,6 @@ static void dtable_dump(FILE *stream, struct kvm_dtable *dtable,
 		dtable->padding[0], dtable->padding[1], dtable->padding[2]);
 }
 
-/* System Register Dump
- *
- * Input Args:
- *   indent - Left margin indent amount
- *   sregs - System registers
- *
- * Output Args:
- *   stream - Output FILE stream
- *
- * Return: None
- *
- * Dumps the state of the system registers given by sregs, to the FILE stream
- * given by steam.
- */
 void sregs_dump(FILE *stream, struct kvm_sregs *sregs,
 		uint8_t indent)
 {
@@ -240,21 +214,6 @@ void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot)
 	}
 }
 
-/* VM Virtual Page Map
- *
- * Input Args:
- *   vm - Virtual Machine
- *   vaddr - VM Virtual Address
- *   paddr - VM Physical Address
- *   pgd_memslot - Memory region slot for new virtual translation tables
- *
- * Output Args: None
- *
- * Return: None
- *
- * Within the VM given by vm, creates a virtual translation for the page
- * starting at vaddr to the page starting at paddr.
- */
 void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 	uint32_t pgd_memslot)
 {
@@ -326,20 +285,6 @@ void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 	pte[index[0]].present = 1;
 }
 
-/* Virtual Translation Tables Dump
- *
- * Input Args:
- *   vm - Virtual Machine
- *   indent - Left margin indent amount
- *
- * Output Args:
- *   stream - Output FILE stream
- *
- * Return: None
- *
- * Dumps to the FILE stream given by stream, the contents of all the
- * virtual translation tables for the VM given by vm.
- */
 void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
 {
 	struct pageMapL4Entry *pml4e, *pml4e_start;
@@ -421,7 +366,8 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
 	}
 }
 
-/* Set Unusable Segment
+/*
+ * Set Unusable Segment
  *
  * Input Args: None
  *
@@ -430,7 +376,7 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
  *
  * Return: None
  *
- * Sets the segment register pointed to by segp to an unusable state.
+ * Sets the segment register pointed to by @segp to an unusable state.
  */
 static void kvm_seg_set_unusable(struct kvm_segment *segp)
 {
@@ -460,7 +406,8 @@ static void kvm_seg_fill_gdt_64bit(struct kvm_vm *vm, struct kvm_segment *segp)
 }
 
 
-/* Set Long Mode Flat Kernel Code Segment
+/*
+ * Set Long Mode Flat Kernel Code Segment
  *
  * Input Args:
  *   vm - VM whose GDT is being filled, or NULL to only write segp
@@ -471,8 +418,8 @@ static void kvm_seg_fill_gdt_64bit(struct kvm_vm *vm, struct kvm_segment *segp)
  *
  * Return: None
  *
- * Sets up the KVM segment pointed to by segp, to be a code segment
- * with the selector value given by selector.
+ * Sets up the KVM segment pointed to by @segp, to be a code segment
+ * with the selector value given by @selector.
  */
 static void kvm_seg_set_kernel_code_64bit(struct kvm_vm *vm, uint16_t selector,
 	struct kvm_segment *segp)
@@ -491,7 +438,8 @@ static void kvm_seg_set_kernel_code_64bit(struct kvm_vm *vm, uint16_t selector,
 		kvm_seg_fill_gdt_64bit(vm, segp);
 }
 
-/* Set Long Mode Flat Kernel Data Segment
+/*
+ * Set Long Mode Flat Kernel Data Segment
  *
  * Input Args:
  *   vm - VM whose GDT is being filled, or NULL to only write segp
@@ -502,8 +450,8 @@ static void kvm_seg_set_kernel_code_64bit(struct kvm_vm *vm, uint16_t selector,
  *
  * Return: None
  *
- * Sets up the KVM segment pointed to by segp, to be a data segment
- * with the selector value given by selector.
+ * Sets up the KVM segment pointed to by @segp, to be a data segment
+ * with the selector value given by @selector.
  */
 static void kvm_seg_set_kernel_data_64bit(struct kvm_vm *vm, uint16_t selector,
 	struct kvm_segment *segp)
@@ -521,24 +469,6 @@ static void kvm_seg_set_kernel_data_64bit(struct kvm_vm *vm, uint16_t selector,
 		kvm_seg_fill_gdt_64bit(vm, segp);
 }
 
-/* Address Guest Virtual to Guest Physical
- *
- * Input Args:
- *   vm - Virtual Machine
- *   gpa - VM virtual address
- *
- * Output Args: None
- *
- * Return:
- *   Equivalent VM physical address
- *
- * Translates the VM virtual address given by gva to a VM physical
- * address and then locates the memory region containing the VM
- * physical address, within the VM given by vm.  When found, the host
- * virtual address providing the memory to the vm physical address is returned.
- * A TEST_ASSERT failure occurs if no region containing translated
- * VM virtual address exists.
- */
 vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
 {
 	uint16_t index[4];
@@ -576,8 +506,7 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
 	return (pte[index[0]].address * vm->page_size) + (gva & 0xfffu);
 
 unmapped_gva:
-	TEST_ASSERT(false, "No mapping for vm virtual address, "
-		    "gva: 0x%lx", gva);
+	TEST_FAIL("No mapping for vm virtual address, gva: 0x%lx", gva);
 	exit(EXIT_FAILURE);
 }
 
@@ -634,18 +563,13 @@ static void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_m
 		break;
 
 	default:
-		TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", vm->mode);
+		TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode);
 	}
 
 	sregs.cr3 = vm->pgd;
 	vcpu_sregs_set(vm, vcpuid, &sregs);
 }
-/* Adds a vCPU with reasonable defaults (i.e., a stack)
- *
- * Input Args:
- *   vcpuid - The id of the VCPU to add to the VM.
- *   guest_code - The vCPU's entry point
- */
+
 void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
 {
 	struct kvm_mp_state mp_state;
@@ -670,7 +594,8 @@ void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
 	vcpu_set_mp_state(vm, vcpuid, &mp_state);
 }
 
-/* Allocate an instance of struct kvm_cpuid2
+/*
+ * Allocate an instance of struct kvm_cpuid2
  *
  * Input Args: None
  *
@@ -703,7 +628,8 @@ static struct kvm_cpuid2 *allocate_kvm_cpuid2(void)
 	return cpuid;
 }
 
-/* KVM Supported CPUID Get
+/*
+ * KVM Supported CPUID Get
  *
  * Input Args: None
  *
@@ -735,11 +661,12 @@ struct kvm_cpuid2 *kvm_get_supported_cpuid(void)
 	return cpuid;
 }
 
-/* Locate a cpuid entry.
+/*
+ * Locate a cpuid entry.
  *
  * Input Args:
- *   cpuid: The cpuid.
  *   function: The function of the cpuid entry to find.
+ *   index: The index of the cpuid entry.
  *
  * Output Args: None
  *
@@ -766,7 +693,8 @@ kvm_get_supported_cpuid_index(uint32_t function, uint32_t index)
 	return entry;
 }
 
-/* VM VCPU CPUID Set
+/*
+ * VM VCPU CPUID Set
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -793,20 +721,6 @@ void vcpu_set_cpuid(struct kvm_vm *vm,
 
 }
 
-/* Create a VM with reasonable defaults
- *
- * Input Args:
- *   vcpuid - The id of the single VCPU to add to the VM.
- *   extra_mem_pages - The size of extra memories to add (this will
- *                     decide how much extra space we will need to
- *                     setup the page tables using mem slot 0)
- *   guest_code - The vCPU's entry point
- *
- * Output Args: None
- *
- * Return:
- *   Pointer to opaque structure that describes the created VM.
- */
 struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
 				 void *guest_code)
 {
@@ -837,7 +751,8 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
 	return vm;
 }
 
-/* VCPU Get MSR
+/*
+ * VCPU Get MSR
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -869,7 +784,8 @@ uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index)
 	return buffer.entry.data;
 }
 
-/* _VCPU Set MSR
+/*
+ * _VCPU Set MSR
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -902,7 +818,8 @@ int _vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index,
 	return r;
 }
 
-/* VCPU Set MSR
+/*
+ * VCPU Set MSR
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -926,22 +843,6 @@ void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index,
 		"  rc: %i errno: %i", r, errno);
 }
 
-/* VM VCPU Args Set
- *
- * Input Args:
- *   vm - Virtual Machine
- *   vcpuid - VCPU ID
- *   num - number of arguments
- *   ... - arguments, each of type uint64_t
- *
- * Output Args: None
- *
- * Return: None
- *
- * Sets the first num function input arguments to the values
- * given as variable args.  Each of the variable args is expected to
- * be of type uint64_t.
- */
 void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...)
 {
 	va_list ap;
@@ -976,22 +877,6 @@ void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...)
 	va_end(ap);
 }
 
-/*
- * VM VCPU Dump
- *
- * Input Args:
- *   vm - Virtual Machine
- *   vcpuid - VCPU ID
- *   indent - Left margin indent amount
- *
- * Output Args:
- *   stream - Output FILE stream
- *
- * Return: None
- *
- * Dumps the current state of the VCPU specified by vcpuid, within the VM
- * given by vm, to the FILE stream given by stream.
- */
 void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent)
 {
 	struct kvm_regs regs;
diff --git a/tools/testing/selftests/kvm/lib/x86_64/svm.c b/tools/testing/selftests/kvm/lib/x86_64/svm.c
index 6e05a8fc3fe0..c42401068373 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/svm.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/svm.c
@@ -154,7 +154,7 @@ void nested_svm_check_supported(void)
 		kvm_get_supported_cpuid_entry(0x80000001);
 
 	if (!(entry->ecx & CPUID_SVM)) {
-		fprintf(stderr, "nested SVM not enabled, skipping test\n");
+		print_skip("nested SVM not enabled");
 		exit(KSFT_SKIP);
 	}
 }
diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
index 7aaa99ca4dbc..6f17f69394be 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
@@ -191,7 +191,7 @@ bool load_vmcs(struct vmx_pages *vmx)
 		if (evmcs_vmptrld(vmx->enlightened_vmcs_gpa,
 				  vmx->enlightened_vmcs))
 			return false;
-		current_evmcs->revision_id = vmcs_revision();
+		current_evmcs->revision_id = EVMCS_VERSION;
 	}
 
 	return true;
@@ -381,7 +381,7 @@ void nested_vmx_check_supported(void)
 	struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
 
 	if (!(entry->ecx & CPUID_VMX)) {
-		fprintf(stderr, "nested VMX not enabled, skipping test\n");
+		print_skip("nested VMX not enabled");
 		exit(KSFT_SKIP);
 	}
 }
diff --git a/tools/testing/selftests/kvm/s390x/memop.c b/tools/testing/selftests/kvm/s390x/memop.c
index 9edaa9a134ce..9f49ead380ab 100644
--- a/tools/testing/selftests/kvm/s390x/memop.c
+++ b/tools/testing/selftests/kvm/s390x/memop.c
@@ -40,7 +40,7 @@ int main(int argc, char *argv[])
 
 	maxsize = kvm_check_cap(KVM_CAP_S390_MEM_OP);
 	if (!maxsize) {
-		fprintf(stderr, "CAP_S390_MEM_OP not supported -> skip test\n");
+		print_skip("CAP_S390_MEM_OP not supported");
 		exit(KSFT_SKIP);
 	}
 	if (maxsize > sizeof(mem1))
diff --git a/tools/testing/selftests/kvm/s390x/resets.c b/tools/testing/selftests/kvm/s390x/resets.c
index 1485bc6c8999..b143db6d8693 100644
--- a/tools/testing/selftests/kvm/s390x/resets.c
+++ b/tools/testing/selftests/kvm/s390x/resets.c
@@ -20,29 +20,42 @@ struct kvm_s390_irq buf[VCPU_ID + LOCAL_IRQS];
 
 struct kvm_vm *vm;
 struct kvm_run *run;
-struct kvm_sync_regs *regs;
-static uint64_t regs_null[16];
-
-static uint64_t crs[16] = { 0x40000ULL,
-			    0x42000ULL,
-			    0, 0, 0, 0, 0,
-			    0x43000ULL,
-			    0, 0, 0, 0, 0,
-			    0x44000ULL,
-			    0, 0
-};
+struct kvm_sync_regs *sync_regs;
+static uint8_t regs_null[512];
 
 static void guest_code_initial(void)
 {
-	/* Round toward 0 */
-	uint32_t fpc = 0x11;
+	/* set several CRs to "safe" value */
+	unsigned long cr2_59 = 0x10;	/* enable guarded storage */
+	unsigned long cr8_63 = 0x1;	/* monitor mask = 1 */
+	unsigned long cr10 = 1;		/* PER START */
+	unsigned long cr11 = -1;	/* PER END */
+
 
 	/* Dirty registers */
 	asm volatile (
-		"	lctlg	0,15,%0\n"
-		"	sfpc	%1\n"
-		: : "Q" (crs), "d" (fpc));
-	GUEST_SYNC(0);
+		"	lghi	2,0x11\n"	/* Round toward 0 */
+		"	sfpc	2\n"		/* set fpc to !=0 */
+		"	lctlg	2,2,%0\n"
+		"	lctlg	8,8,%1\n"
+		"	lctlg	10,10,%2\n"
+		"	lctlg	11,11,%3\n"
+		/* now clobber some general purpose regs */
+		"	llihh	0,0xffff\n"
+		"	llihl	1,0x5555\n"
+		"	llilh	2,0xaaaa\n"
+		"	llill	3,0x0000\n"
+		/* now clobber a floating point reg */
+		"	lghi	4,0x1\n"
+		"	cdgbr	0,4\n"
+		/* now clobber an access reg */
+		"	sar	9,4\n"
+		/* We embed diag 501 here to control register content */
+		"	diag 0,0,0x501\n"
+		:
+		: "m" (cr2_59), "m" (cr8_63), "m" (cr10), "m" (cr11)
+		/* no clobber list as this should not return */
+		);
 }
 
 static void test_one_reg(uint64_t id, uint64_t value)
@@ -53,7 +66,7 @@ static void test_one_reg(uint64_t id, uint64_t value)
 	reg.addr = (uintptr_t)&eval_reg;
 	reg.id = id;
 	vcpu_get_reg(vm, VCPU_ID, &reg);
-	TEST_ASSERT(eval_reg == value, "value == %s", value);
+	TEST_ASSERT(eval_reg == value, "value == 0x%lx", value);
 }
 
 static void assert_noirq(void)
@@ -87,6 +100,31 @@ static void assert_clear(void)
 
 	vcpu_fpu_get(vm, VCPU_ID, &fpu);
 	TEST_ASSERT(!memcmp(&fpu.fprs, regs_null, sizeof(fpu.fprs)), "fprs == 0");
+
+	/* sync regs */
+	TEST_ASSERT(!memcmp(sync_regs->gprs, regs_null, sizeof(sync_regs->gprs)),
+		    "gprs0-15 == 0 (sync_regs)");
+
+	TEST_ASSERT(!memcmp(sync_regs->acrs, regs_null, sizeof(sync_regs->acrs)),
+		    "acrs0-15 == 0 (sync_regs)");
+
+	TEST_ASSERT(!memcmp(sync_regs->vrs, regs_null, sizeof(sync_regs->vrs)),
+		    "vrs0-15 == 0 (sync_regs)");
+}
+
+static void assert_initial_noclear(void)
+{
+	TEST_ASSERT(sync_regs->gprs[0] == 0xffff000000000000UL,
+		    "gpr0 == 0xffff000000000000 (sync_regs)");
+	TEST_ASSERT(sync_regs->gprs[1] == 0x0000555500000000UL,
+		    "gpr1 == 0x0000555500000000 (sync_regs)");
+	TEST_ASSERT(sync_regs->gprs[2] == 0x00000000aaaa0000UL,
+		    "gpr2 == 0x00000000aaaa0000 (sync_regs)");
+	TEST_ASSERT(sync_regs->gprs[3] == 0x0000000000000000UL,
+		    "gpr3 == 0x0000000000000000 (sync_regs)");
+	TEST_ASSERT(sync_regs->fprs[0] == 0x3ff0000000000000UL,
+		    "fpr0 == 0f1 (sync_regs)");
+	TEST_ASSERT(sync_regs->acrs[9] == 1, "ar9 == 1 (sync_regs)");
 }
 
 static void assert_initial(void)
@@ -94,12 +132,32 @@ static void assert_initial(void)
 	struct kvm_sregs sregs;
 	struct kvm_fpu fpu;
 
+	/* KVM_GET_SREGS */
 	vcpu_sregs_get(vm, VCPU_ID, &sregs);
-	TEST_ASSERT(sregs.crs[0] == 0xE0UL, "cr0 == 0xE0");
-	TEST_ASSERT(sregs.crs[14] == 0xC2000000UL, "cr14 == 0xC2000000");
+	TEST_ASSERT(sregs.crs[0] == 0xE0UL, "cr0 == 0xE0 (KVM_GET_SREGS)");
+	TEST_ASSERT(sregs.crs[14] == 0xC2000000UL,
+		    "cr14 == 0xC2000000 (KVM_GET_SREGS)");
 	TEST_ASSERT(!memcmp(&sregs.crs[1], regs_null, sizeof(sregs.crs[1]) * 12),
-		    "cr1-13 == 0");
-	TEST_ASSERT(sregs.crs[15] == 0, "cr15 == 0");
+		    "cr1-13 == 0 (KVM_GET_SREGS)");
+	TEST_ASSERT(sregs.crs[15] == 0, "cr15 == 0 (KVM_GET_SREGS)");
+
+	/* sync regs */
+	TEST_ASSERT(sync_regs->crs[0] == 0xE0UL, "cr0 == 0xE0 (sync_regs)");
+	TEST_ASSERT(sync_regs->crs[14] == 0xC2000000UL,
+		    "cr14 == 0xC2000000 (sync_regs)");
+	TEST_ASSERT(!memcmp(&sync_regs->crs[1], regs_null, 8 * 12),
+		    "cr1-13 == 0 (sync_regs)");
+	TEST_ASSERT(sync_regs->crs[15] == 0, "cr15 == 0 (sync_regs)");
+	TEST_ASSERT(sync_regs->fpc == 0, "fpc == 0 (sync_regs)");
+	TEST_ASSERT(sync_regs->todpr == 0, "todpr == 0 (sync_regs)");
+	TEST_ASSERT(sync_regs->cputm == 0, "cputm == 0 (sync_regs)");
+	TEST_ASSERT(sync_regs->ckc == 0, "ckc == 0 (sync_regs)");
+	TEST_ASSERT(sync_regs->pp == 0, "pp == 0 (sync_regs)");
+	TEST_ASSERT(sync_regs->gbea == 1, "gbea == 1 (sync_regs)");
+
+	/* kvm_run */
+	TEST_ASSERT(run->psw_addr == 0, "psw_addr == 0 (kvm_run)");
+	TEST_ASSERT(run->psw_mask == 0, "psw_mask == 0 (kvm_run)");
 
 	vcpu_fpu_get(vm, VCPU_ID, &fpu);
 	TEST_ASSERT(!fpu.fpc, "fpc == 0");
@@ -111,9 +169,19 @@ static void assert_initial(void)
 	test_one_reg(KVM_REG_S390_CLOCK_COMP, 0);
 }
 
+static void assert_normal_noclear(void)
+{
+	TEST_ASSERT(sync_regs->crs[2] == 0x10, "cr2 == 10 (sync_regs)");
+	TEST_ASSERT(sync_regs->crs[8] == 1, "cr10 == 1 (sync_regs)");
+	TEST_ASSERT(sync_regs->crs[10] == 1, "cr10 == 1 (sync_regs)");
+	TEST_ASSERT(sync_regs->crs[11] == -1, "cr11 == -1 (sync_regs)");
+}
+
 static void assert_normal(void)
 {
 	test_one_reg(KVM_REG_S390_PFTOKEN, KVM_S390_PFAULT_TOKEN_INVALID);
+	TEST_ASSERT(sync_regs->pft == KVM_S390_PFAULT_TOKEN_INVALID,
+			"pft == 0xff.....  (sync_regs)");
 	assert_noirq();
 }
 
@@ -134,53 +202,67 @@ static void inject_irq(int cpu_id)
 
 static void test_normal(void)
 {
-	printf("Testing normal reset\n");
+	pr_info("Testing normal reset\n");
 	/* Create VM */
 	vm = vm_create_default(VCPU_ID, 0, guest_code_initial);
 	run = vcpu_state(vm, VCPU_ID);
-	regs = &run->s.regs;
+	sync_regs = &run->s.regs;
 
 	vcpu_run(vm, VCPU_ID);
 
 	inject_irq(VCPU_ID);
 
 	vcpu_ioctl(vm, VCPU_ID, KVM_S390_NORMAL_RESET, 0);
+
+	/* must clears */
 	assert_normal();
+	/* must not clears */
+	assert_normal_noclear();
+	assert_initial_noclear();
+
 	kvm_vm_free(vm);
 }
 
 static void test_initial(void)
 {
-	printf("Testing initial reset\n");
+	pr_info("Testing initial reset\n");
 	vm = vm_create_default(VCPU_ID, 0, guest_code_initial);
 	run = vcpu_state(vm, VCPU_ID);
-	regs = &run->s.regs;
+	sync_regs = &run->s.regs;
 
 	vcpu_run(vm, VCPU_ID);
 
 	inject_irq(VCPU_ID);
 
 	vcpu_ioctl(vm, VCPU_ID, KVM_S390_INITIAL_RESET, 0);
+
+	/* must clears */
 	assert_normal();
 	assert_initial();
+	/* must not clears */
+	assert_initial_noclear();
+
 	kvm_vm_free(vm);
 }
 
 static void test_clear(void)
 {
-	printf("Testing clear reset\n");
+	pr_info("Testing clear reset\n");
 	vm = vm_create_default(VCPU_ID, 0, guest_code_initial);
 	run = vcpu_state(vm, VCPU_ID);
-	regs = &run->s.regs;
+	sync_regs = &run->s.regs;
 
 	vcpu_run(vm, VCPU_ID);
 
 	inject_irq(VCPU_ID);
 
 	vcpu_ioctl(vm, VCPU_ID, KVM_S390_CLEAR_RESET, 0);
+
+	/* must clears */
 	assert_normal();
 	assert_initial();
 	assert_clear();
+
 	kvm_vm_free(vm);
 }
 
diff --git a/tools/testing/selftests/kvm/s390x/sync_regs_test.c b/tools/testing/selftests/kvm/s390x/sync_regs_test.c
index b705637ca14b..5731ccf34917 100644
--- a/tools/testing/selftests/kvm/s390x/sync_regs_test.c
+++ b/tools/testing/selftests/kvm/s390x/sync_regs_test.c
@@ -42,6 +42,13 @@ static void guest_code(void)
 		    " values did not match: 0x%llx, 0x%llx\n", \
 		    left->reg, right->reg)
 
+#define REG_COMPARE32(reg) \
+	TEST_ASSERT(left->reg == right->reg, \
+		    "Register " #reg \
+		    " values did not match: 0x%x, 0x%x\n", \
+		    left->reg, right->reg)
+
+
 static void compare_regs(struct kvm_regs *left, struct kvm_sync_regs *right)
 {
 	int i;
@@ -55,7 +62,7 @@ static void compare_sregs(struct kvm_sregs *left, struct kvm_sync_regs *right)
 	int i;
 
 	for (i = 0; i < 16; i++)
-		REG_COMPARE(acrs[i]);
+		REG_COMPARE32(acrs[i]);
 
 	for (i = 0; i < 16; i++)
 		REG_COMPARE(crs[i]);
@@ -79,7 +86,7 @@ int main(int argc, char *argv[])
 
 	cap = kvm_check_cap(KVM_CAP_SYNC_REGS);
 	if (!cap) {
-		fprintf(stderr, "CAP_SYNC_REGS not supported, skipping test\n");
+		print_skip("CAP_SYNC_REGS not supported");
 		exit(KSFT_SKIP);
 	}
 
@@ -155,7 +162,7 @@ int main(int argc, char *argv[])
 		    "r11 sync regs value incorrect 0x%llx.",
 		    run->s.regs.gprs[11]);
 	TEST_ASSERT(run->s.regs.acrs[0]  == 1 << 11,
-		    "acr0 sync regs value incorrect 0x%llx.",
+		    "acr0 sync regs value incorrect 0x%x.",
 		    run->s.regs.acrs[0]);
 
 	vcpu_regs_get(vm, VCPU_ID, &regs);
diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c
new file mode 100644
index 000000000000..fcc840088c91
--- /dev/null
+++ b/tools/testing/selftests/kvm/steal_time.c
@@ -0,0 +1,352 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * steal/stolen time test
+ *
+ * Copyright (C) 2020, Red Hat, Inc.
+ */
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <time.h>
+#include <sched.h>
+#include <pthread.h>
+#include <linux/kernel.h>
+#include <sys/syscall.h>
+#include <asm/kvm.h>
+#include <asm/kvm_para.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+#define NR_VCPUS		4
+#define ST_GPA_BASE		(1 << 30)
+#define MIN_RUN_DELAY_NS	200000UL
+
+static void *st_gva[NR_VCPUS];
+static uint64_t guest_stolen_time[NR_VCPUS];
+
+#if defined(__x86_64__)
+
+/* steal_time must have 64-byte alignment */
+#define STEAL_TIME_SIZE		((sizeof(struct kvm_steal_time) + 63) & ~63)
+
+static void check_status(struct kvm_steal_time *st)
+{
+	GUEST_ASSERT(!(READ_ONCE(st->version) & 1));
+	GUEST_ASSERT(READ_ONCE(st->flags) == 0);
+	GUEST_ASSERT(READ_ONCE(st->preempted) == 0);
+}
+
+static void guest_code(int cpu)
+{
+	struct kvm_steal_time *st = st_gva[cpu];
+	uint32_t version;
+
+	GUEST_ASSERT(rdmsr(MSR_KVM_STEAL_TIME) == ((uint64_t)st_gva[cpu] | KVM_MSR_ENABLED));
+
+	memset(st, 0, sizeof(*st));
+	GUEST_SYNC(0);
+
+	check_status(st);
+	WRITE_ONCE(guest_stolen_time[cpu], st->steal);
+	version = READ_ONCE(st->version);
+	check_status(st);
+	GUEST_SYNC(1);
+
+	check_status(st);
+	GUEST_ASSERT(version < READ_ONCE(st->version));
+	WRITE_ONCE(guest_stolen_time[cpu], st->steal);
+	check_status(st);
+	GUEST_DONE();
+}
+
+static void steal_time_init(struct kvm_vm *vm)
+{
+	int i;
+
+	if (!(kvm_get_supported_cpuid_entry(KVM_CPUID_FEATURES)->eax &
+	      KVM_FEATURE_STEAL_TIME)) {
+		print_skip("steal-time not supported");
+		exit(KSFT_SKIP);
+	}
+
+	for (i = 0; i < NR_VCPUS; ++i) {
+		int ret;
+
+		vcpu_set_cpuid(vm, i, kvm_get_supported_cpuid());
+
+		/* ST_GPA_BASE is identity mapped */
+		st_gva[i] = (void *)(ST_GPA_BASE + i * STEAL_TIME_SIZE);
+		sync_global_to_guest(vm, st_gva[i]);
+
+		ret = _vcpu_set_msr(vm, i, MSR_KVM_STEAL_TIME, (ulong)st_gva[i] | KVM_STEAL_RESERVED_MASK);
+		TEST_ASSERT(ret == 0, "Bad GPA didn't fail");
+
+		vcpu_set_msr(vm, i, MSR_KVM_STEAL_TIME, (ulong)st_gva[i] | KVM_MSR_ENABLED);
+	}
+}
+
+static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	struct kvm_steal_time *st = addr_gva2hva(vm, (ulong)st_gva[vcpuid]);
+	int i;
+
+	pr_info("VCPU%d:\n", vcpuid);
+	pr_info("    steal:     %lld\n", st->steal);
+	pr_info("    version:   %d\n", st->version);
+	pr_info("    flags:     %d\n", st->flags);
+	pr_info("    preempted: %d\n", st->preempted);
+	pr_info("    u8_pad:    ");
+	for (i = 0; i < 3; ++i)
+		pr_info("%d", st->u8_pad[i]);
+	pr_info("\n    pad:       ");
+	for (i = 0; i < 11; ++i)
+		pr_info("%d", st->pad[i]);
+	pr_info("\n");
+}
+
+#elif defined(__aarch64__)
+
+/* PV_TIME_ST must have 64-byte alignment */
+#define STEAL_TIME_SIZE		((sizeof(struct st_time) + 63) & ~63)
+
+#define SMCCC_ARCH_FEATURES	0x80000001
+#define PV_TIME_FEATURES	0xc5000020
+#define PV_TIME_ST		0xc5000021
+
+struct st_time {
+	uint32_t rev;
+	uint32_t attr;
+	uint64_t st_time;
+};
+
+static int64_t smccc(uint32_t func, uint32_t arg)
+{
+	unsigned long ret;
+
+	asm volatile(
+		"mov	x0, %1\n"
+		"mov	x1, %2\n"
+		"hvc	#0\n"
+		"mov	%0, x0\n"
+	: "=r" (ret) : "r" (func), "r" (arg) :
+	  "x0", "x1", "x2", "x3");
+
+	return ret;
+}
+
+static void check_status(struct st_time *st)
+{
+	GUEST_ASSERT(READ_ONCE(st->rev) == 0);
+	GUEST_ASSERT(READ_ONCE(st->attr) == 0);
+}
+
+static void guest_code(int cpu)
+{
+	struct st_time *st;
+	int64_t status;
+
+	status = smccc(SMCCC_ARCH_FEATURES, PV_TIME_FEATURES);
+	GUEST_ASSERT(status == 0);
+	status = smccc(PV_TIME_FEATURES, PV_TIME_FEATURES);
+	GUEST_ASSERT(status == 0);
+	status = smccc(PV_TIME_FEATURES, PV_TIME_ST);
+	GUEST_ASSERT(status == 0);
+
+	status = smccc(PV_TIME_ST, 0);
+	GUEST_ASSERT(status != -1);
+	GUEST_ASSERT(status == (ulong)st_gva[cpu]);
+
+	st = (struct st_time *)status;
+	GUEST_SYNC(0);
+
+	check_status(st);
+	WRITE_ONCE(guest_stolen_time[cpu], st->st_time);
+	GUEST_SYNC(1);
+
+	check_status(st);
+	WRITE_ONCE(guest_stolen_time[cpu], st->st_time);
+	GUEST_DONE();
+}
+
+static void steal_time_init(struct kvm_vm *vm)
+{
+	struct kvm_device_attr dev = {
+		.group = KVM_ARM_VCPU_PVTIME_CTRL,
+		.attr = KVM_ARM_VCPU_PVTIME_IPA,
+	};
+	int i, ret;
+
+	ret = _vcpu_ioctl(vm, 0, KVM_HAS_DEVICE_ATTR, &dev);
+	if (ret != 0 && errno == ENXIO) {
+		print_skip("steal-time not supported");
+		exit(KSFT_SKIP);
+	}
+
+	for (i = 0; i < NR_VCPUS; ++i) {
+		uint64_t st_ipa;
+
+		vcpu_ioctl(vm, i, KVM_HAS_DEVICE_ATTR, &dev);
+
+		dev.addr = (uint64_t)&st_ipa;
+
+		/* ST_GPA_BASE is identity mapped */
+		st_gva[i] = (void *)(ST_GPA_BASE + i * STEAL_TIME_SIZE);
+		sync_global_to_guest(vm, st_gva[i]);
+
+		st_ipa = (ulong)st_gva[i] | 1;
+		ret = _vcpu_ioctl(vm, i, KVM_SET_DEVICE_ATTR, &dev);
+		TEST_ASSERT(ret == -1 && errno == EINVAL, "Bad IPA didn't report EINVAL");
+
+		st_ipa = (ulong)st_gva[i];
+		vcpu_ioctl(vm, i, KVM_SET_DEVICE_ATTR, &dev);
+
+		ret = _vcpu_ioctl(vm, i, KVM_SET_DEVICE_ATTR, &dev);
+		TEST_ASSERT(ret == -1 && errno == EEXIST, "Set IPA twice without EEXIST");
+
+	}
+}
+
+static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	struct st_time *st = addr_gva2hva(vm, (ulong)st_gva[vcpuid]);
+
+	pr_info("VCPU%d:\n", vcpuid);
+	pr_info("    rev:     %d\n", st->rev);
+	pr_info("    attr:    %d\n", st->attr);
+	pr_info("    st_time: %ld\n", st->st_time);
+}
+
+#endif
+
+static long get_run_delay(void)
+{
+	char path[64];
+	long val[2];
+	FILE *fp;
+
+	sprintf(path, "/proc/%ld/schedstat", syscall(SYS_gettid));
+	fp = fopen(path, "r");
+	fscanf(fp, "%ld %ld ", &val[0], &val[1]);
+	fclose(fp);
+
+	return val[1];
+}
+
+static void *do_steal_time(void *arg)
+{
+	struct timespec ts, stop;
+
+	clock_gettime(CLOCK_MONOTONIC, &ts);
+	stop = timespec_add_ns(ts, MIN_RUN_DELAY_NS);
+
+	while (1) {
+		clock_gettime(CLOCK_MONOTONIC, &ts);
+		if (timespec_to_ns(timespec_sub(ts, stop)) >= 0)
+			break;
+	}
+
+	return NULL;
+}
+
+static void run_vcpu(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	struct ucall uc;
+
+	vcpu_args_set(vm, vcpuid, 1, vcpuid);
+
+	vcpu_ioctl(vm, vcpuid, KVM_RUN, NULL);
+
+	switch (get_ucall(vm, vcpuid, &uc)) {
+	case UCALL_SYNC:
+	case UCALL_DONE:
+		break;
+	case UCALL_ABORT:
+		TEST_ASSERT(false, "%s at %s:%ld", (const char *)uc.args[0],
+			    __FILE__, uc.args[1]);
+	default:
+		TEST_ASSERT(false, "Unexpected exit: %s",
+			    exit_reason_str(vcpu_state(vm, vcpuid)->exit_reason));
+	}
+}
+
+int main(int ac, char **av)
+{
+	struct kvm_vm *vm;
+	pthread_attr_t attr;
+	pthread_t thread;
+	cpu_set_t cpuset;
+	unsigned int gpages;
+	long stolen_time;
+	long run_delay;
+	bool verbose;
+	int i;
+
+	verbose = ac > 1 && (!strncmp(av[1], "-v", 3) || !strncmp(av[1], "--verbose", 10));
+
+	/* Set CPU affinity so we can force preemption of the VCPU */
+	CPU_ZERO(&cpuset);
+	CPU_SET(0, &cpuset);
+	pthread_attr_init(&attr);
+	pthread_attr_setaffinity_np(&attr, sizeof(cpu_set_t), &cpuset);
+	pthread_setaffinity_np(pthread_self(), sizeof(cpu_set_t), &cpuset);
+
+	/* Create a one VCPU guest and an identity mapped memslot for the steal time structure */
+	vm = vm_create_default(0, 0, guest_code);
+	gpages = vm_calc_num_guest_pages(VM_MODE_DEFAULT, STEAL_TIME_SIZE * NR_VCPUS);
+	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, ST_GPA_BASE, 1, gpages, 0);
+	virt_map(vm, ST_GPA_BASE, ST_GPA_BASE, gpages, 0);
+	ucall_init(vm, NULL);
+
+	/* Add the rest of the VCPUs */
+	for (i = 1; i < NR_VCPUS; ++i)
+		vm_vcpu_add_default(vm, i, guest_code);
+
+	steal_time_init(vm);
+
+	/* Run test on each VCPU */
+	for (i = 0; i < NR_VCPUS; ++i) {
+		/* First VCPU run initializes steal-time */
+		run_vcpu(vm, i);
+
+		/* Second VCPU run, expect guest stolen time to be <= run_delay */
+		run_vcpu(vm, i);
+		sync_global_from_guest(vm, guest_stolen_time[i]);
+		stolen_time = guest_stolen_time[i];
+		run_delay = get_run_delay();
+		TEST_ASSERT(stolen_time <= run_delay,
+			    "Expected stolen time <= %ld, got %ld",
+			    run_delay, stolen_time);
+
+		/* Steal time from the VCPU. The steal time thread has the same CPU affinity as the VCPUs. */
+		run_delay = get_run_delay();
+		pthread_create(&thread, &attr, do_steal_time, NULL);
+		do
+			pthread_yield();
+		while (get_run_delay() - run_delay < MIN_RUN_DELAY_NS);
+		pthread_join(thread, NULL);
+		run_delay = get_run_delay() - run_delay;
+		TEST_ASSERT(run_delay >= MIN_RUN_DELAY_NS,
+			    "Expected run_delay >= %ld, got %ld",
+			    MIN_RUN_DELAY_NS, run_delay);
+
+		/* Run VCPU again to confirm stolen time is consistent with run_delay */
+		run_vcpu(vm, i);
+		sync_global_from_guest(vm, guest_stolen_time[i]);
+		stolen_time = guest_stolen_time[i] - stolen_time;
+		TEST_ASSERT(stolen_time >= run_delay,
+			    "Expected stolen time >= %ld, got %ld",
+			    run_delay, stolen_time);
+
+		if (verbose) {
+			pr_info("VCPU%d: total-stolen-time=%ld test-stolen-time=%ld", i,
+				guest_stolen_time[i], stolen_time);
+			if (stolen_time == run_delay)
+				pr_info(" (BONUS: guest test-stolen-time even exactly matches test-run_delay)");
+			pr_info("\n");
+			steal_time_dump(vm, i);
+		}
+	}
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c
index 63cc9c3f5ab6..140e91901582 100644
--- a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c
+++ b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c
@@ -72,7 +72,7 @@ int main(int argc, char *argv[])
 
 	entry = kvm_get_supported_cpuid_entry(1);
 	if (!(entry->ecx & X86_FEATURE_XSAVE)) {
-		printf("XSAVE feature not supported, skipping test\n");
+		print_skip("XSAVE feature not supported");
 		return 0;
 	}
 
@@ -101,12 +101,12 @@ int main(int argc, char *argv[])
 			vcpu_sregs_set(vm, VCPU_ID, &sregs);
 			break;
 		case UCALL_ABORT:
-			TEST_ASSERT(false, "Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit.");
+			TEST_FAIL("Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit.");
 			break;
 		case UCALL_DONE:
 			goto done;
 		default:
-			TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
+			TEST_FAIL("Unknown ucall %lu", uc.cmd);
 		}
 	}
 
diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c
index 92915e6408e7..e6e62e5e75b2 100644
--- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c
@@ -21,10 +21,10 @@
 
 void l2_guest_code(void)
 {
-	GUEST_SYNC(6);
-
 	GUEST_SYNC(7);
 
+	GUEST_SYNC(8);
+
 	/* Done, exit to L1 and never come back.  */
 	vmcall();
 }
@@ -50,12 +50,17 @@ void l1_guest_code(struct vmx_pages *vmx_pages)
 
 	GUEST_SYNC(5);
 	GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa);
+	current_evmcs->revision_id = -1u;
+	GUEST_ASSERT(vmlaunch());
+	current_evmcs->revision_id = EVMCS_VERSION;
+	GUEST_SYNC(6);
+
 	GUEST_ASSERT(!vmlaunch());
 	GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa);
-	GUEST_SYNC(8);
+	GUEST_SYNC(9);
 	GUEST_ASSERT(!vmresume());
 	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
-	GUEST_SYNC(9);
+	GUEST_SYNC(10);
 }
 
 void guest_code(struct vmx_pages *vmx_pages)
@@ -67,6 +72,10 @@ void guest_code(struct vmx_pages *vmx_pages)
 		l1_guest_code(vmx_pages);
 
 	GUEST_DONE();
+
+	/* Try enlightened vmptrld with an incorrect GPA */
+	evmcs_vmptrld(0xdeadbeef, vmx_pages->enlightened_vmcs);
+	GUEST_ASSERT(vmlaunch());
 }
 
 int main(int argc, char *argv[])
@@ -87,7 +96,7 @@ int main(int argc, char *argv[])
 
 	if (!kvm_check_cap(KVM_CAP_NESTED_STATE) ||
 	    !kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) {
-		printf("capabilities not available, skipping test\n");
+		print_skip("capabilities not available");
 		exit(KSFT_SKIP);
 	}
 
@@ -109,20 +118,20 @@ int main(int argc, char *argv[])
 
 		switch (get_ucall(vm, VCPU_ID, &uc)) {
 		case UCALL_ABORT:
-			TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0],
-				    __FILE__, uc.args[1]);
+			TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0],
+		      		  __FILE__, uc.args[1]);
 			/* NOT REACHED */
 		case UCALL_SYNC:
 			break;
 		case UCALL_DONE:
-			goto done;
+			goto part1_done;
 		default:
-			TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
+			TEST_FAIL("Unknown ucall %lu", uc.cmd);
 		}
 
 		/* UCALL_SYNC is handled here.  */
 		TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") &&
-			    uc.args[1] == stage, "Unexpected register values vmexit #%lx, got %lx",
+			    uc.args[1] == stage, "Stage %d: Unexpected register values vmexit, got %lx",
 			    stage, (ulong)uc.args[1]);
 
 		state = vcpu_save_state(vm, VCPU_ID);
@@ -147,6 +156,10 @@ int main(int argc, char *argv[])
 			    (ulong) regs2.rdi, (ulong) regs2.rsi);
 	}
 
-done:
+part1_done:
+	_vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN,
+		    "Unexpected successful VMEnter with invalid eVMCS pointer!");
+
 	kvm_vm_free(vm);
 }
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
index 443a2b54645b..83323f3d7ca0 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
@@ -66,7 +66,7 @@ static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries,
 
 		TEST_ASSERT((entry->function >= 0x40000000) &&
 			    (entry->function <= 0x4000000A),
-			    "function %lx is our of supported range",
+			    "function %x is our of supported range",
 			    entry->function);
 
 		TEST_ASSERT(entry->index == 0,
@@ -141,8 +141,7 @@ int main(int argc, char *argv[])
 
 	rv = kvm_check_cap(KVM_CAP_HYPERV_CPUID);
 	if (!rv) {
-		fprintf(stderr,
-			"KVM_CAP_HYPERV_CPUID not supported, skip test\n");
+		print_skip("KVM_CAP_HYPERV_CPUID not supported");
 		exit(KSFT_SKIP);
 	}
 
@@ -160,8 +159,7 @@ int main(int argc, char *argv[])
 	free(hv_cpuid_entries);
 
 	if (!kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) {
-		fprintf(stderr,
-			"Enlightened VMCS is unsupported, skip related test\n");
+		print_skip("Enlightened VMCS is unsupported");
 		goto vm_free;
 	}
 
diff --git a/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c b/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c
index 00bb97d76000..e6480fd5c4bd 100644
--- a/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c
+++ b/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c
@@ -44,7 +44,7 @@ void *thr(void *arg)
 	struct kvm_run *run = tc->run;
 
 	res = ioctl(kvmcpu, KVM_RUN, 0);
-	printf("ret1=%d exit_reason=%d suberror=%d\n",
+	pr_info("ret1=%d exit_reason=%d suberror=%d\n",
 		res, run->exit_reason, run->internal.suberror);
 
 	return 0;
@@ -93,12 +93,12 @@ int main(void)
 	int warnings_before, warnings_after;
 
 	if (!is_intel_cpu()) {
-		printf("Must be run on an Intel CPU, skipping test\n");
+		print_skip("Must be run on an Intel CPU");
 		exit(KSFT_SKIP);
 	}
 
 	if (vm_is_unrestricted_guest(NULL)) {
-		printf("Unrestricted guest must be disabled, skipping test\n");
+		print_skip("Unrestricted guest must be disabled");
 		exit(KSFT_SKIP);
 	}
 
diff --git a/tools/testing/selftests/kvm/x86_64/platform_info_test.c b/tools/testing/selftests/kvm/x86_64/platform_info_test.c
index f9334bd3cce9..1e89688cbbbf 100644
--- a/tools/testing/selftests/kvm/x86_64/platform_info_test.c
+++ b/tools/testing/selftests/kvm/x86_64/platform_info_test.c
@@ -58,8 +58,7 @@ static void test_msr_platform_info_enabled(struct kvm_vm *vm)
 			exit_reason_str(run->exit_reason));
 	get_ucall(vm, VCPU_ID, &uc);
 	TEST_ASSERT(uc.cmd == UCALL_SYNC,
-			"Received ucall other than UCALL_SYNC: %u\n",
-			ucall);
+			"Received ucall other than UCALL_SYNC: %lu\n", uc.cmd);
 	TEST_ASSERT((uc.args[1] & MSR_PLATFORM_INFO_MAX_TURBO_RATIO) ==
 		MSR_PLATFORM_INFO_MAX_TURBO_RATIO,
 		"Expected MSR_PLATFORM_INFO to have max turbo ratio mask: %i.",
@@ -89,8 +88,7 @@ int main(int argc, char *argv[])
 
 	rv = kvm_check_cap(KVM_CAP_MSR_PLATFORM_INFO);
 	if (!rv) {
-		fprintf(stderr,
-			"KVM_CAP_MSR_PLATFORM_INFO not supported, skip test\n");
+		print_skip("KVM_CAP_MSR_PLATFORM_INFO not supported");
 		exit(KSFT_SKIP);
 	}
 
diff --git a/tools/testing/selftests/kvm/x86_64/set_memory_region_test.c b/tools/testing/selftests/kvm/x86_64/set_memory_region_test.c
new file mode 100644
index 000000000000..c6691cff4e19
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/set_memory_region_test.c
@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <fcntl.h>
+#include <pthread.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include <linux/compiler.h>
+
+#include <test_util.h>
+#include <kvm_util.h>
+#include <processor.h>
+
+#define VCPU_ID 0
+
+/*
+ * Somewhat arbitrary location and slot, intended to not overlap anything.  The
+ * location and size are specifically 2mb sized/aligned so that the initial
+ * region corresponds to exactly one large page.
+ */
+#define MEM_REGION_GPA		0xc0000000
+#define MEM_REGION_SIZE		0x200000
+#define MEM_REGION_SLOT		10
+
+static void guest_code(void)
+{
+	uint64_t val;
+
+	do {
+		val = READ_ONCE(*((uint64_t *)MEM_REGION_GPA));
+	} while (!val);
+
+	if (val != 1)
+		ucall(UCALL_ABORT, 1, val);
+
+	GUEST_DONE();
+}
+
+static void *vcpu_worker(void *data)
+{
+	struct kvm_vm *vm = data;
+	struct kvm_run *run;
+	struct ucall uc;
+	uint64_t cmd;
+
+	/*
+	 * Loop until the guest is done.  Re-enter the guest on all MMIO exits,
+	 * which will occur if the guest attempts to access a memslot while it
+	 * is being moved.
+	 */
+	run = vcpu_state(vm, VCPU_ID);
+	do {
+		vcpu_run(vm, VCPU_ID);
+	} while (run->exit_reason == KVM_EXIT_MMIO);
+
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+		    "Unexpected exit reason = %d", run->exit_reason);
+
+	cmd = get_ucall(vm, VCPU_ID, &uc);
+	TEST_ASSERT(cmd == UCALL_DONE, "Unexpected val in guest = %lu", uc.args[0]);
+	return NULL;
+}
+
+static void test_move_memory_region(void)
+{
+	pthread_t vcpu_thread;
+	struct kvm_vm *vm;
+	uint64_t *hva;
+	uint64_t gpa;
+
+	vm = vm_create_default(VCPU_ID, 0, guest_code);
+
+	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+
+	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS_THP,
+				    MEM_REGION_GPA, MEM_REGION_SLOT,
+				    MEM_REGION_SIZE / getpagesize(), 0);
+
+	/*
+	 * Allocate and map two pages so that the GPA accessed by guest_code()
+	 * stays valid across the memslot move.
+	 */
+	gpa = vm_phy_pages_alloc(vm, 2, MEM_REGION_GPA, MEM_REGION_SLOT);
+	TEST_ASSERT(gpa == MEM_REGION_GPA, "Failed vm_phy_pages_alloc\n");
+
+	virt_map(vm, MEM_REGION_GPA, MEM_REGION_GPA, 2, 0);
+
+	/* Ditto for the host mapping so that both pages can be zeroed. */
+	hva = addr_gpa2hva(vm, MEM_REGION_GPA);
+	memset(hva, 0, 2 * 4096);
+
+	pthread_create(&vcpu_thread, NULL, vcpu_worker, vm);
+
+	/* Ensure the guest thread is spun up. */
+	usleep(100000);
+
+	/*
+	 * Shift the region's base GPA.  The guest should not see "2" as the
+	 * hva->gpa translation is misaligned, i.e. the guest is accessing a
+	 * different host pfn.
+	 */
+	vm_mem_region_move(vm, MEM_REGION_SLOT, MEM_REGION_GPA - 4096);
+	WRITE_ONCE(*hva, 2);
+
+	usleep(100000);
+
+	/*
+	 * Note, value in memory needs to be changed *before* restoring the
+	 * memslot, else the guest could race the update and see "2".
+	 */
+	WRITE_ONCE(*hva, 1);
+
+	/* Restore the original base, the guest should see "1". */
+	vm_mem_region_move(vm, MEM_REGION_SLOT, MEM_REGION_GPA);
+
+	pthread_join(vcpu_thread, NULL);
+
+	kvm_vm_free(vm);
+}
+
+int main(int argc, char *argv[])
+{
+	int i, loops;
+
+	/* Tell stdout not to buffer its content */
+	setbuf(stdout, NULL);
+
+	if (argc > 1)
+		loops = atoi(argv[1]);
+	else
+		loops = 10;
+
+	for (i = 0; i < loops; i++)
+		test_move_memory_region();
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c
index 8c063646f2a0..8230b6bc6b8f 100644
--- a/tools/testing/selftests/kvm/x86_64/smm_test.c
+++ b/tools/testing/selftests/kvm/x86_64/smm_test.c
@@ -117,7 +117,7 @@ int main(int argc, char *argv[])
 		vcpu_alloc_vmx(vm, &vmx_pages_gva);
 		vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva);
 	} else {
-		printf("will skip SMM test with VMX enabled\n");
+		pr_info("will skip SMM test with VMX enabled\n");
 		vcpu_args_set(vm, VCPU_ID, 1, 0);
 	}
 
diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c
index 3ab5ec3da9f4..5b1a016edf55 100644
--- a/tools/testing/selftests/kvm/x86_64/state_test.c
+++ b/tools/testing/selftests/kvm/x86_64/state_test.c
@@ -139,7 +139,7 @@ int main(int argc, char *argv[])
 		vcpu_alloc_vmx(vm, &vmx_pages_gva);
 		vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva);
 	} else {
-		printf("will skip nested state checks\n");
+		pr_info("will skip nested state checks\n");
 		vcpu_args_set(vm, VCPU_ID, 1, 0);
 	}
 
@@ -152,20 +152,20 @@ int main(int argc, char *argv[])
 
 		switch (get_ucall(vm, VCPU_ID, &uc)) {
 		case UCALL_ABORT:
-			TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0],
-				    __FILE__, uc.args[1]);
+			TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0],
+			       	  __FILE__, uc.args[1]);
 			/* NOT REACHED */
 		case UCALL_SYNC:
 			break;
 		case UCALL_DONE:
 			goto done;
 		default:
-			TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
+			TEST_FAIL("Unknown ucall %lu", uc.cmd);
 		}
 
 		/* UCALL_SYNC is handled here.  */
 		TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") &&
-			    uc.args[1] == stage, "Unexpected register values vmexit #%lx, got %lx",
+			    uc.args[1] == stage, "Stage %d: Unexpected register values vmexit, got %lx",
 			    stage, (ulong)uc.args[1]);
 
 		state = vcpu_save_state(vm, VCPU_ID);
diff --git a/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c b/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c
index e280f68f6365..0e1adb4e3199 100644
--- a/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c
+++ b/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c
@@ -61,16 +61,14 @@ int main(int argc, char *argv[])
 
 		switch (get_ucall(vm, VCPU_ID, &uc)) {
 		case UCALL_ABORT:
-			TEST_ASSERT(false, "%s",
-				    (const char *)uc.args[0]);
+			TEST_FAIL("%s", (const char *)uc.args[0]);
 			/* NOT REACHED */
 		case UCALL_SYNC:
 			break;
 		case UCALL_DONE:
 			goto done;
 		default:
-			TEST_ASSERT(false,
-				    "Unknown ucall 0x%x.", uc.cmd);
+			TEST_FAIL("Unknown ucall 0x%lx.", uc.cmd);
 		}
 	}
 done:
diff --git a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
index 5c8224256294..d672f0a473f8 100644
--- a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
@@ -91,11 +91,11 @@ int main(int argc, char *argv[])
 
 	cap = kvm_check_cap(KVM_CAP_SYNC_REGS);
 	if ((cap & TEST_SYNC_FIELDS) != TEST_SYNC_FIELDS) {
-		fprintf(stderr, "KVM_CAP_SYNC_REGS not supported, skipping test\n");
+		print_skip("KVM_CAP_SYNC_REGS not supported");
 		exit(KSFT_SKIP);
 	}
 	if ((cap & INVALID_SYNC_FIELD) != 0) {
-		fprintf(stderr, "The \"invalid\" field is not invalid, skipping test\n");
+		print_skip("The \"invalid\" field is not invalid");
 		exit(KSFT_SKIP);
 	}
 
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c
index 5dfb53546a26..fe40ade06a49 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c
@@ -78,10 +78,10 @@ int main(int argc, char *argv[])
 
 		switch (get_ucall(vm, VCPU_ID, &uc)) {
 		case UCALL_ABORT:
-			TEST_ASSERT(false, "%s", (const char *)uc.args[0]);
+			TEST_FAIL("%s", (const char *)uc.args[0]);
 			/* NOT REACHED */
 		default:
-			TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
+			TEST_FAIL("Unknown ucall %lu", uc.cmd);
 		}
 	}
 }
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
index a223a6401258..e894a638a155 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
@@ -21,7 +21,7 @@
 
 /* The memory slot index to track dirty pages */
 #define TEST_MEM_SLOT_INDEX		1
-#define TEST_MEM_SIZE			3
+#define TEST_MEM_PAGES			3
 
 /* L1 guest test virtual memory offset */
 #define GUEST_TEST_MEM			0xc0000000
@@ -91,15 +91,14 @@ int main(int argc, char *argv[])
 	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
 				    GUEST_TEST_MEM,
 				    TEST_MEM_SLOT_INDEX,
-				    TEST_MEM_SIZE,
+				    TEST_MEM_PAGES,
 				    KVM_MEM_LOG_DIRTY_PAGES);
 
 	/*
 	 * Add an identity map for GVA range [0xc0000000, 0xc0002000).  This
 	 * affects both L1 and L2.  However...
 	 */
-	virt_map(vm, GUEST_TEST_MEM, GUEST_TEST_MEM,
-		 TEST_MEM_SIZE * 4096, 0);
+	virt_map(vm, GUEST_TEST_MEM, GUEST_TEST_MEM, TEST_MEM_PAGES, 0);
 
 	/*
 	 * ... pages in the L2 GPA range [0xc0001000, 0xc0003000) will map to
@@ -113,11 +112,11 @@ int main(int argc, char *argv[])
 	nested_map(vmx, vm, NESTED_TEST_MEM1, GUEST_TEST_MEM, 4096, 0);
 	nested_map(vmx, vm, NESTED_TEST_MEM2, GUEST_TEST_MEM, 4096, 0);
 
-	bmap = bitmap_alloc(TEST_MEM_SIZE);
+	bmap = bitmap_alloc(TEST_MEM_PAGES);
 	host_test_mem = addr_gpa2hva(vm, GUEST_TEST_MEM);
 
 	while (!done) {
-		memset(host_test_mem, 0xaa, TEST_MEM_SIZE * 4096);
+		memset(host_test_mem, 0xaa, TEST_MEM_PAGES * 4096);
 		_vcpu_run(vm, VCPU_ID);
 		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
 			    "Unexpected exit reason: %u (%s),\n",
@@ -126,8 +125,8 @@ int main(int argc, char *argv[])
 
 		switch (get_ucall(vm, VCPU_ID, &uc)) {
 		case UCALL_ABORT:
-			TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0],
-				    __FILE__, uc.args[1]);
+			TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0],
+			       	  __FILE__, uc.args[1]);
 			/* NOT REACHED */
 		case UCALL_SYNC:
 			/*
@@ -152,7 +151,7 @@ int main(int argc, char *argv[])
 			done = true;
 			break;
 		default:
-			TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
+			TEST_FAIL("Unknown ucall %lu", uc.cmd);
 		}
 	}
 }
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c
index 9ef7fab39d48..54cdefdfb49d 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c
@@ -212,7 +212,7 @@ void test_vmx_nested_state(struct kvm_vm *vm)
 	test_nested_state(vm, state);
 	vcpu_nested_state_get(vm, VCPU_ID, state);
 	TEST_ASSERT(state->size >= sizeof(*state) && state->size <= state_sz,
-		    "Size must be between %d and %d.  The size returned was %d.",
+		    "Size must be between %ld and %d.  The size returned was %d.",
 		    sizeof(*state), state_sz, state->size);
 	TEST_ASSERT(state->hdr.vmx.vmxon_pa == -1ull, "vmxon_pa must be -1ull.");
 	TEST_ASSERT(state->hdr.vmx.vmcs12_pa == -1ull, "vmcs_pa must be -1ull.");
@@ -228,7 +228,7 @@ int main(int argc, char *argv[])
 	have_evmcs = kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS);
 
 	if (!kvm_check_cap(KVM_CAP_NESTED_STATE)) {
-		printf("KVM_CAP_NESTED_STATE not available, skipping test\n");
+		print_skip("KVM_CAP_NESTED_STATE not available");
 		exit(KSFT_SKIP);
 	}
 
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
index 69e482a95c47..fbe8417cbc2c 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
@@ -121,8 +121,8 @@ static void l1_guest_code(struct vmx_pages *vmx_pages)
 
 static void report(int64_t val)
 {
-	printf("IA32_TSC_ADJUST is %ld (%lld * TSC_ADJUST_VALUE + %lld).\n",
-	       val, val / TSC_ADJUST_VALUE, val % TSC_ADJUST_VALUE);
+	pr_info("IA32_TSC_ADJUST is %ld (%lld * TSC_ADJUST_VALUE + %lld).\n",
+		val, val / TSC_ADJUST_VALUE, val % TSC_ADJUST_VALUE);
 }
 
 int main(int argc, char *argv[])
@@ -150,7 +150,7 @@ int main(int argc, char *argv[])
 
 		switch (get_ucall(vm, VCPU_ID, &uc)) {
 		case UCALL_ABORT:
-			TEST_ASSERT(false, "%s", (const char *)uc.args[0]);
+			TEST_FAIL("%s", (const char *)uc.args[0]);
 			/* NOT REACHED */
 		case UCALL_SYNC:
 			report(uc.args[1]);
@@ -158,7 +158,7 @@ int main(int argc, char *argv[])
 		case UCALL_DONE:
 			goto done;
 		default:
-			TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
+			TEST_FAIL("Unknown ucall %lu", uc.cmd);
 		}
 	}
 
diff --git a/tools/testing/selftests/kvm/x86_64/xss_msr_test.c b/tools/testing/selftests/kvm/x86_64/xss_msr_test.c
index 851ea81b9d9f..3529376747c2 100644
--- a/tools/testing/selftests/kvm/x86_64/xss_msr_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xss_msr_test.c
@@ -51,7 +51,7 @@ int main(int argc, char *argv[])
 		xss_supported = entry && !!(entry->eax & X86_FEATURE_XSAVES);
 	}
 	if (!xss_supported) {
-		printf("IA32_XSS is not supported by the vCPU.\n");
+		print_skip("IA32_XSS is not supported by the vCPU");
 		exit(KSFT_SKIP);
 	}